Video Compression | Papers With Code

<!doctype html> <html lang="en"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> <script> const GTAG_ENABLED = true ; const GTAG_TRACKING_ID = "UA-121182717-1"; const SENTRY_DSN_FRONTEND = "".trim(); const GLOBAL_CSRF_TOKEN = '2dhE9sJRZuXwvtBaJy3oj8wT6Lgy6JfuDtOFcaRGEUXkUzyomlJu3yTtbTqtqi3v'; const MEDIA_URL = "https://production-media.paperswithcode.com/"; const ASSETS_URL = "https://production-assets.paperswithcode.com"; run_after_frontend_loaded = window.run_after_frontend_loaded || []; </script> <link rel="preconnect" href="https://production-assets.paperswithcode.com"><link rel="dns-prefetch" href="https://production-assets.paperswithcode.com"><link rel="preload" as="font" type="font/woff2" href="https://production-assets.paperswithcode.com/perf/fonts/65e877e527022735c1a1.woff2" crossorigin><link rel="preload" as="font" type="font/woff2" href="https://production-assets.paperswithcode.com/perf/fonts/917632e36982ca7933c8.woff2" crossorigin><link rel="preload" as="font" type="font/woff2" href="https://production-assets.paperswithcode.com/perf/fonts/f1405bd8a987c2ea8a67.woff2" crossorigin><script>(()=>{if(GTAG_ENABLED){const t=document.createElement("script");function n(){window.dataLayer.push(arguments)}t.src=`https://www.googletagmanager.com/gtag/js?id=${GTAG_TRACKING_ID}`,document.head.appendChild(t),window.dataLayer=window.dataLayer||[],window.gtag=n,n("js",new Date),n("config",GTAG_TRACKING_ID),window.captureOutboundLink=function(t){n("event","click",{event_category:"outbound",event_label:t})}}else window.captureOutboundLink=function(n){document.location=n}})();</script><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/766.4af6b88b.js"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/2.6da00df7.js"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/351.a22a9607.js"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/101.5f271f23.js"><link rel="preload" as="style" href="https://production-assets.paperswithcode.com/perf/918.c41196c3.css"><link rel="preload" as="style" href="https://production-assets.paperswithcode.com/perf/view_task.8e3945a3.css"><link rel="preload" as="script" href="https://production-assets.paperswithcode.com/perf/view_task.e61ab167.js"><link rel="stylesheet" href="https://production-assets.paperswithcode.com/perf/918.c41196c3.css"><link rel="stylesheet" href="https://production-assets.paperswithcode.com/perf/view_task.8e3945a3.css">  <title>Video Compression | Papers With Code</title> <meta name="description" content="**Video Compression** is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data. <span class="description-source">Source: [Adversarial Video Compression Guided by Soft Edge Detection ](https://arxiv.org/abs/1811.10673)</span>" />  <meta property="og:title" content="Papers with Code - Video Compression"> <meta property="og:description" content="**Video Compression** is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data. <span class="description-source">Source: [Adversarial Video Compression Guided by Soft Edge Detection ](https://arxiv.org/abs/1811.10673)</span>"> <meta property="og:image" content="https://production-media.paperswithcode.com/tasks/1204px-Girl_with_a_Pearl_Earring_pixelated_vmayh0I.jpg"> <meta property="og:url" content="https://paperswithcode.com/task/video-compression">  <meta name="twitter:card" content="summary_large_image"> <meta name="twitter:site" content="@paperswithcode"> <meta name="twitter:title" content="Papers with Code - Video Compression"> <meta name="twitter:description" content="**Video Compression** is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data. <span class="description-source">Source: [Adversarial Video Compression Guided by Soft Edge Detection ](https://arxiv.org/abs/1811.10673)</span>"> <meta name="twitter:creator" content="@paperswithcode"> <meta name="twitter:url" content="https://paperswithcode.com/task/video-compression"> <meta name="twitter:domain" content="paperswithcode.com">  <script type="application/ld+json">{ "@context": "http://schema.org", "@graph": { "@type": "CreativeWork", "@id": "video-compression", "name": "Video Compression", "description": "**Video Compression** is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data.\r\n\r\n\r\n\u003Cspan class=\"description-source\"\u003ESource: [Adversarial Video Compression Guided by Soft Edge Detection ](https://arxiv.org/abs/1811.10673)\u003C/span\u003E", "url": "https://paperswithcode.com/task/video-compression", "image": "https://production-media.paperswithcode.com/tasks/1204px-Girl_with_a_Pearl_Earring_pixelated_vmayh0I.jpg", "subjectOf": [ { "@type": "CreativeWork", "@id": "computer-vision", "name": "Computer Vision", "description": "Browse 1547 tasks \u2022 3353 datasets \u2022 5187 ", "image": "https://paperswithcode.com/static/sota.jpeg", "headline": "Browse state-of-the-art in ML leaderboards \u2022 57166 papers with code." }, { "@type": "CreativeWork", "@id": "video", "name": "Video", "description": "", "image": "https://production-media.paperswithcode.com/tasks/default.gif", "subjectOf": [ { "@type": "CreativeWork", "@id": "computer-vision", "name": "Computer Vision", "description": "Browse 1547 tasks \u2022 3353 datasets \u2022 5187 ", "image": "https://paperswithcode.com/static/sota.jpeg", "headline": "Browse state-of-the-art in ML leaderboards \u2022 57166 papers with code." } ], "headline": "Video" } ], "headline": "Video Compression" } }</script> <meta name="theme-color" content="#fff"/> <link rel="manifest" href="https://production-assets.paperswithcode.com/static/manifest.web.json"> </head> <body> <nav class="navbar navbar-expand-lg navbar-light header"> <a class="navbar-brand" href="/"> <span class=" icon-wrapper" data-name="pwc"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path d="M88 128h48v256H88zm144 0h48v256h-48zm-72 16h48v224h-48zm144 0h48v224h-48zm72-16h48v256h-48z"/><path d="M104 104V56H16v400h88v-48H64V104zm304-48v48h40v304h-40v48h88V56z"/></svg></span> </a> <div class="navbar-mobile-twitter d-lg-none"> <a rel="noreferrer" href="https://twitter.com/paperswithcode"> <span class=" icon-wrapper icon-fa icon-fa-brands" data-name="twitter"><svg viewBox="0 0 512.001 515.25" xmlns="http://www.w3.org/2000/svg"><path d="M459.37 152.016c.326 4.548.326 9.097.326 13.645 0 138.72-105.583 298.558-298.559 298.558C101.685 464.22 46.457 447 0 417.114c8.447.973 16.568 1.298 25.34 1.298 49.054 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.113-72.772 6.499.975 12.996 1.624 19.819 1.624 9.42 0 18.843-1.3 27.613-3.573-48.08-9.747-84.142-51.98-84.142-102.984v-1.3c13.968 7.798 30.213 12.67 47.43 13.32-28.263-18.843-46.78-51.006-46.78-87.391 0-19.492 5.196-37.36 14.294-52.954 51.654 63.674 129.3 105.258 216.364 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.827 46.782-104.934 104.934-104.934 30.214 0 57.502 12.67 76.671 33.136 23.715-4.548 46.455-13.319 66.599-25.34-7.798 24.367-24.366 44.834-46.132 57.828 21.117-2.274 41.584-8.122 60.426-16.244-14.292 20.791-32.161 39.309-52.628 54.253z"/></svg></span> </a> </div> <button class="navbar-toggler" type="button" data-toggle="collapse" data-bs-toggle="collapse" data-target="#top-menu" data-bs-target="#top-menu" aria-controls="top-menu" aria-expanded="false" aria-label="Toggle navigation" > <span class="navbar-toggler-icon"></span> </button> <div class="collapse navbar-collapse" id="top-menu"> <ul class="navbar-nav mr-auto navbar-nav__left light-header"> <li class="nav-item header-search"> <form action="/search" method="get" id="id_global_search_form" autocomplete="off"> <input type="text" name="q_meta" style="display:none" id="q_meta" /> <input type="hidden" name="q_type" id="q_type" /> <input id="id_global_search_input" autocomplete="off" value="" name='q' class="global-search" type="search" placeholder='Search'/> <button type="submit" class="icon"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="search"><svg viewBox="0 0 512.025 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M508.5 482.6c4.7 4.7 4.7 12.3 0 17l-9.9 9.9c-4.7 4.7-12.3 4.7-17 0l-129-129c-2.2-2.3-3.5-5.3-3.5-8.5v-10.2C312 396 262.5 417 208 417 93.1 417 0 323.9 0 209S93.1 1 208 1s208 93.1 208 208c0 54.5-21 104-55.3 141.1H371c3.2 0 6.2 1.2 8.5 3.5zM208 385c97.3 0 176-78.7 176-176S305.3 33 208 33 32 111.7 32 209s78.7 176 176 176z"/></svg></span></button> </form> </li> <li class="nav-item"> <a class="nav-link" href="/sota"> Browse State-of-the-Art </a> </li> <li class="nav-item"> <a class="nav-link" href="/datasets"> Datasets </a> </li> <li class="nav-item"> <a class="nav-link" href="/methods">Methods</a> </li> <li class="nav-item dropdown"> <a class="nav-link dropdown-toggle" role="button" id="navbarDropdownRepro" data-toggle="dropdown" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false" > More </a> <div class="dropdown-menu" aria-labelledby="navbarDropdownRepro"> <a class="dropdown-item" href="/newsletter">Newsletter</a> <a class="dropdown-item" href="/rc2022">RC2022</a> <div class="dropdown-divider"></div> <a class="dropdown-item" href="/about">About</a> <a class="dropdown-item" href="/trends">Trends</a> <a class="dropdown-item" href="https://portal.paperswithcode.com/"> Portals </a> <a class="dropdown-item" href="/libraries"> Libraries </a> </div> </li> </ul> <ul class="navbar-nav ml-auto navbar-nav__right navbar-subscribe justify-content-center align-items-center"> <li class="nav-item"> <a class="nav-link" rel="noreferrer" href="https://twitter.com/paperswithcode"> <span class="nav-link-social-icon icon-wrapper icon-fa icon-fa-brands" data-name="twitter"><svg viewBox="0 0 512.001 515.25" xmlns="http://www.w3.org/2000/svg"><path d="M459.37 152.016c.326 4.548.326 9.097.326 13.645 0 138.72-105.583 298.558-298.559 298.558C101.685 464.22 46.457 447 0 417.114c8.447.973 16.568 1.298 25.34 1.298 49.054 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.113-72.772 6.499.975 12.996 1.624 19.819 1.624 9.42 0 18.843-1.3 27.613-3.573-48.08-9.747-84.142-51.98-84.142-102.984v-1.3c13.968 7.798 30.213 12.67 47.43 13.32-28.263-18.843-46.78-51.006-46.78-87.391 0-19.492 5.196-37.36 14.294-52.954 51.654 63.674 129.3 105.258 216.364 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.827 46.782-104.934 104.934-104.934 30.214 0 57.502 12.67 76.671 33.136 23.715-4.548 46.455-13.319 66.599-25.34-7.798 24.367-24.366 44.834-46.132 57.828 21.117-2.274 41.584-8.122 60.426-16.244-14.292 20.791-32.161 39.309-52.628 54.253z"/></svg></span> </a> </li> <li class="nav-item"> <a id="signin-link" class="nav-link" href="/accounts/login?next=/task/video-compression">Sign In</a> </li> </ul> </div> </nav>  <div class="modal fade" id="emailModal" tabindex="-1" role="dialog" aria-labelledby="emailModalLabel" aria-hidden="true"> <div class="modal-dialog" role="document"> <div class="modal-content"> <div class="modal-header"> <h3 class="modal-title" id="emailModalLabel">Subscribe to the PwC Newsletter</h3> <button type="button" class="close" data-dismiss="modal" data-bs-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <form action="" method="post"> <div class="modal-body"> <div class="modal-body-info-text"> Stay informed on the latest trending ML papers with code, research developments, libraries, methods, and datasets.<br/><br/> <a href="/newsletter">Read previous issues</a> </div> <input type="hidden" name="csrfmiddlewaretoken" value="2dhE9sJRZuXwvtBaJy3oj8wT6Lgy6JfuDtOFcaRGEUXkUzyomlJu3yTtbTqtqi3v"> <input placeholder="Enter your email" type="email" class="form-control pwc-email" name="address" id="id_address" max_length="100" required> </div> <div class="modal-footer"> <button type="submit" class="btn btn-primary">Subscribe</button> </div> </form> </div> </div> </div>  <div class="modal fade" id="loginModal" tabindex="-1" role="dialog" aria-labelledby="loginModalLabel" aria-hidden="true"> <div class="modal-dialog" role="document"> <div class="modal-content"> <div class="modal-header"> <h5 class="modal-title" id="loginModalLabel">Join the community</h5> <button type="button" class="close btn-close" data-dismiss="modal" data-bs-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <div class="login-modal-message"> You need to <a href="/accounts/login?next=/task/video-compression">log in</a> to edit.<br/> You can <a href="/accounts/register?next=/task/video-compression">create a new account</a> if you don't have one.<br/><br/> </div> </div> </div> </div>   <div class="modal fade" id="editTask" role="dialog" aria-labelledby="editTaskLabel" aria-hidden="true"> <div class="modal-dialog modal-lg" role="document"> <div class="modal-content"> <div class="modal-header"> <h5 class="modal-title" id="editTaskLabel">Edit task</h5> <button type="button" class="close btn-close" data-bs-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <div class="modal-body"> <form action="" method="post" enctype="multipart/form-data"> <input type="hidden" name="csrfmiddlewaretoken" value="ktvFSQ33WRX3t9JvsIFd4pGLjncq23PYohCpApU2AwuwCDTMObeo1iIZMOMxpZMd"> <div id="div_id_task_name" class="form-group"> <label for="id_task_name" class="col-form-label requiredField"> Task name:<span class="asteriskField">*</span> </label> <div class=""> <input type="text" name="task_name" value="Video Compression" maxlength="200" class="textinput textInput form-control" required="" id="id_task_name" readonly > </div> </div> <div id="div_id_task_area" class="form-group"> <label for="id_task_area" class=" requiredField"> Top-level area:<span class="asteriskField">*</span> </label> <div class=""> <select name="task_area" class="select form-control" required id="id_task_area"> <option value="">---------</option> <option value="17">Adversarial</option> <option value="18">Audio</option> <option value="11">Computer Code</option> <option value="3" selected>Computer Vision</option> <option value="9">Graphs</option> <option value="15">Knowledge Base</option> <option value="7">Medical</option> <option value="6">Methodology</option> <option value="5">Miscellaneous</option> <option value="12">Music</option> <option value="4">Natural Language Processing</option> <option value="13">Playing Games</option> <option value="14">Reasoning</option> <option value="16">Robots</option> <option value="10">Speech</option> <option value="8">Time Series</option> </select> </div> </div> <div id="div_id_task_parent" class="form-group"> <label for="id_task_parent" class=""> Parent task (if any): </label> <div class=""> <select name="task_parent" class="modelselect2 form-control" id="id_task_parent" data-autocomplete-light-language="en" data-autocomplete-light-url="/tag-autocomplete/" data-autocomplete-light-function="select2"> <option value="">---------</option> <option value="913" selected>Video</option> </select> </div> </div> <div id="div_id_description" class="form-group"> <label for="id_description" class=""> Description with markdown (optional): </label> <div class=""> <textarea name="description" cols="40" rows="3" class="textarea form-control" id="id_description"> **Video Compression** is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data. <span class="description-source">Source: [Adversarial Video Compression Guided by Soft Edge Detection ](https://arxiv.org/abs/1811.10673)</span></textarea> </div> </div> <div id="div_id_image" class="form-group"> <label for="id_image" class=""> Image </label> <div class=""> Currently: <a href="https://production-media.paperswithcode.com/tasks/1204px-Girl_with_a_Pearl_Earring_pixelated_vmayh0I.jpg">tasks/1204px-Girl_with_a_Pearl_Earring_pixelated_vmayh0I.jpg</a> <input type="checkbox" name="image-clear" id="image-clear_id"> <label for="image-clear_id">Clear</label><br> Change: <input type="file" name="image" accept="image/*" class="clearablefileinput form-control-file" id="id_image"> </div> </div> <div class="modal-footer"> <button type="submit" class="btn btn-primary"> Submit </button> </div> </form> </div> </div> </div> </div>  <div class="modal fade" id="addRow" role="dialog" aria-labelledby="addRowLabel" aria-hidden="true"> <div class="modal-dialog" role="document"> <div class="modal-content"> <div class="modal-header"> <h5 class="modal-title" id="addRowLabel">Add a new evaluation result row</h5> <button type="button" class="close btn-close" data-bs-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <form action="" method="post"> <div class="modal-body"> <input type="hidden" name="csrfmiddlewaretoken" value="ktvFSQ33WRX3t9JvsIFd4pGLjncq23PYohCpApU2AwuwCDTMObeo1iIZMOMxpZMd"> <input id="id_task" disabled="disabled" type="hidden" value="733"/> <div id="div_id_paper" class="form-group"> <label for="id_paper" class=" requiredField"> Paper title:<span class="asteriskField">*</span> </label> <div class=""> <select name="paper" class="modelselect2 form-control" required id="id_paper" data-autocomplete-light-language="en" data-autocomplete-light-url="/paper-autocomplete/" data-autocomplete-light-function="select2"> <option value="" selected>---------</option> </select> </div> </div> <div id="div_id_dataset" class="form-group"> <label for="id_dataset" class=" requiredField"> Dataset:<span class="asteriskField">*</span> </label> <div class=""> <select name="dataset" class="modelselect2 form-control" required id="id_dataset" data-autocomplete-light-language="en" data-autocomplete-light-url="/dataset-autocomplete/" data-autocomplete-light-function="select2"> <option value="" selected>---------</option> </select> </div> </div> <div id="div_id_model_name" class="form-group"> <label for="id_model_name" class=" requiredField"> Model name:<span class="asteriskField">*</span> </label> <div class=""> <input type="text" name="model_name" class="textinput textInput form-control" required id="id_model_name"> </div> </div> <div id="div_id_metric" class="form-group"> <label for="id_metric" class=" requiredField"> Metric name:<span class="asteriskField">*</span> </label> <div class=""> <select name="metric" class="modelselect2 form-control" required id="id_metric" data-autocomplete-light-language="en" data-autocomplete-light-url="/metric-autocomplete/" data-autocomplete-light-function="select2"> <option value="" selected>---------</option> </select> </div> </div> <div id="sota-metric-names"> </div> <div class="form-group"> <div id="div_id_metric_higher_is_better" class="form-check"> <input type="checkbox" name="metric_higher_is_better" class="checkboxinput form-check-input" id="id_metric_higher_is_better"> <label for="id_metric_higher_is_better" class="form-check-label"> Higher is better (for the metric) </label> </div> </div> <div id="div_id_metric_value" class="form-group"> <label for="id_metric_value" class=" requiredField"> Metric value:<span class="asteriskField">*</span> </label> <div class=""> <input type="text" name="metric_value" class="textinput textInput form-control" required id="id_metric_value"> </div> </div> <div id="sota-metric-values"> </div> <div class="form-group"> <div id="div_id_uses_additional_data" class="form-check"> <input type="checkbox" name="uses_additional_data" class="checkboxinput form-check-input" id="id_uses_additional_data"> <label for="id_uses_additional_data" class="form-check-label"> Uses extra training data </label> </div> </div> <div id="div_id_evaluated_on" class="form-group"> <label for="id_evaluated_on" class=""> Data evaluated on </label> <div class=""> <input type="text" name="evaluated_on" autocomplete="off" class="dateinput form-control" id="id_evaluated_on"> </div> </div> </div> <div class="modal-footer"> <button type="submit" class="btn btn-primary">Submit </button> </div> </form> </div> </div> </div> </div> <div class="container content content-buffer "> <main> <div class="row task-content" style="margin-top: 3rem;">  <div class="dataset-header"> <a href="/area/computer-vision"> <span class="badge badge-primary"> <span class=" icon-wrapper icon-fa icon-fa-solid" data-name="images"><svg viewBox="0 0 576 514.999" xmlns="http://www.w3.org/2000/svg"><path d="M480 417.998v16c0 26.51-21.49 48-48 48H48c-26.51 0-48-21.49-48-48v-256c0-26.51 21.49-48 48-48h16v208c0 44.113 35.888 80 80 80h336zm96-80c0 26.51-21.49 48-48 48H144c-26.51 0-48-21.49-48-48v-256c0-26.51 21.49-48 48-48h384c26.51 0 48 21.49 48 48v256zm-320-208c0-26.51-21.49-48-48-48s-48 21.49-48 48 21.49 48 48 48 48-21.49 48-48zm-96 144v48h352v-112l-87.514-87.514c-4.687-4.687-12.285-4.687-16.971 0L272 257.999l-39.514-39.515c-4.688-4.686-12.285-4.686-16.972 0z"/></svg></span> <span>Computer Vision</span> </span> </a> </div> <div class="artefact-header"> <div class="float-right task-edit"> <div class="dropdown edit-button"> <a data-bs-toggle="modal" data-bs-target="#loginModal"> <span class="badge badge-method-edit" style="padding-top:10px;"><span class=" icon-wrapper icon-fa icon-fa-solid" data-name="edit"><svg viewBox="0 0 576 514.999" xmlns="http://www.w3.org/2000/svg"><path d="M402.6 85.198l90.2 90.2c3.8 3.8 3.8 10 0 13.8l-218.399 218.4-92.8 10.3c-12.4 1.4-22.9-9.1-21.5-21.5l10.3-92.8 218.4-218.4c3.799-3.8 10-3.8 13.799 0zm162-22.9c15.2 15.2 15.2 39.9 0 55.2l-35.4 35.4c-3.8 3.8-10 3.8-13.8 0l-90.2-90.2c-3.8-3.8-3.8-10 0-13.8l35.4-35.4c15.3-15.2 40-15.2 55.2 0zM384 348.198c0-3.2 1.3-6.2 3.5-8.5l40-40c7.6-7.5 20.5-2.2 20.5 8.5v157.8c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48v-352c0-26.5 21.5-48 48-48h285.8c10.7 0 16.1 12.9 8.5 20.5l-40 40c-2.3 2.2-5.3 3.5-8.5 3.5H64v320h320v-101.8z"/></svg></span> Edit</span> </a> </div> </div> <h1 id="task-home">Video Compression</h1> <div class="artefact-information"> <p> 129 papers with code • 0 benchmarks • 5 datasets </p> </div> </div> <div class="col-lg-9">  <div class="description"> <div class="description-content"> <p><strong>Video Compression</strong> is a process of reducing the size of an image or video file by exploiting spatial and temporal redundancies within an image or video frame and across multiple video frames. The ultimate goal of a successful Video Compression system is to reduce data volume while retaining the perceptual quality of the decompressed data.</p> <p><span class="description-source">Source: <a href="https://arxiv.org/abs/1811.10673">Adversarial Video Compression Guided by Soft Edge Detection </a></span></p> </div> </div>  <div class="image-container task-image-mobile"> <a href="https://production-media.paperswithcode.com/thumbnails/task/task-0000000733-7b89a5de.jpg" data-lightbox="imageresource"> <img id="imageresource" width=100% src="https://production-media.paperswithcode.com/thumbnails/task/task-0000000733-7b89a5de.jpg"> </a> </div>  <div class="task-benchmarks"> <div id="benchmarks" class="collapsed"> <div class="title"> <h2 id="benchmarks">Benchmarks <div class="float-right"> <div class="dropdown edit-button task-add-a-result"> <a data-bs-toggle="modal" data-bs-target="#loginModal"> <span class="badge badge-primary" style="font-size:12px;"> Add a Result</span> </a> </div> </div> </h2> These leaderboards are used to track progress in Video Compression <hr> </div> <div class="sota-no-sota"> No evaluation results yet. Help compare methods by <a data-bs-toggle="modal" data-bs-target="#loginModal">submitting evaluation metrics</a>. </div> </div> </div>  <div class="task-started"> <div class="title task-libraries"> <h2 id="task-libraries">Libraries <span class="lib-info" data-bs-toggle="popover" data-bs-placement="top" data-bs-trigger="hover" data-bs-title="Libraries" data-bs-content="These libraries are updated daily, based on the papers assigned to this task. If you think a Library is missing, make sure this library is added as code to the papers it implements, and that the papers have been assigned to this task." ><span class=" icon-wrapper icon-ion" data-name="information-circle-outline"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M248 64C146.39 64 64 146.39 64 248s82.39 184 184 184 184-82.39 184-184S349.61 64 248 64z" fill="none" stroke="#000" stroke-miterlimit="10" stroke-width="32"/><path fill="none" stroke="#000" stroke-linecap="round" stroke-linejoin="round" stroke-width="32" d="M220 220h32v116"/><path fill="none" stroke="#000" stroke-linecap="round" stroke-miterlimit="10" stroke-width="32" d="M208 340h88"/><path d="M248 130a26 26 0 1 0 26 26 26 26 0 0 0-26-26z"/></svg></span></span> </h2> Use these libraries to find Video Compression models and implementations <hr> <div id="libraries-short-list"> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/RenYang-home/OpenDVC" onclick="captureOutboundLink('https://github.com/RenYang-home/OpenDVC'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> RenYang-home/OpenDVC </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 4 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 219 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/KUIS-AI-Tekalp-Research-Group/video-compression" onclick="captureOutboundLink('https://github.com/KUIS-AI-Tekalp-Research-Group/video-compression'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> KUIS-AI-Tekalp-Research-Group/video… </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 3 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 22 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/SaipingZhang/DVC_P" onclick="captureOutboundLink('https://github.com/SaipingZhang/DVC_P'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> SaipingZhang/DVC_P </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 3 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 10 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/InterDigitalInc/CompressAI" onclick="captureOutboundLink('https://github.com/InterDigitalInc/CompressAI'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> InterDigitalInc/CompressAI </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 2 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 1,207 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="table-options"> <a href="#" id="libraries-see-more-trigger">See all 6</a> libraries. </div> </div> <div id="libraries-full-list" style="display:none"> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/RenYang-home/OpenDVC" onclick="captureOutboundLink('https://github.com/RenYang-home/OpenDVC'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> RenYang-home/OpenDVC </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 4 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 219 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/KUIS-AI-Tekalp-Research-Group/video-compression" onclick="captureOutboundLink('https://github.com/KUIS-AI-Tekalp-Research-Group/video-compression'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> KUIS-AI-Tekalp-Research-Group/video… </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 3 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 22 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/SaipingZhang/DVC_P" onclick="captureOutboundLink('https://github.com/SaipingZhang/DVC_P'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> SaipingZhang/DVC_P </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 3 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 10 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/InterDigitalInc/CompressAI" onclick="captureOutboundLink('https://github.com/InterDigitalInc/CompressAI'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> InterDigitalInc/CompressAI </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 2 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 1,207 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/xinjie-q/distributed-dvc" onclick="captureOutboundLink('https://github.com/xinjie-q/distributed-dvc'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> xinjie-q/distributed-dvc </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 2 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 30 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="row task-library"> <div class="col-12 col-md-6"> <a href="https://github.com/tianyuan168326/videosemanticcompression-pytorch" onclick="captureOutboundLink('https://github.com/tianyuan168326/videosemanticcompression-pytorch'); return true;"> <div class="library-logo"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> </div> tianyuan168326/videosemanticcompres… </a> </div> <div class="col-6 col-md-3"> <span class="task-library-pwc-count"> 2 papers </span> </div> <div class="col-6 col-md-3"> <div class="library-stars text-nowrap"> 16 <span class=" icon-wrapper icon-ion" data-name="star"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M394 480a16 16 0 0 1-9.39-3L256 383.76 127.39 477a16 16 0 0 1-24.55-18.08L153 310.35 23 221.2a16 16 0 0 1 9-29.2h160.38l48.4-148.95a16 16 0 0 1 30.44 0l48.4 149H480a16 16 0 0 1 9.05 29.2L359 310.35l50.13 148.53A16 16 0 0 1 394 480z"/></svg></span> </div> </div> </div> <div class="table-options"> <a href="#" id="libraries-see-less-trigger">Collapse 6</a> libraries. </div> </div> </div> </div>  <div class="title"> <h2 id="datasets">Datasets</h2> <hr> <div class="task-datasets"> <div class="col-md-12"> <ul class="list-unstyled"> <li> <a href="/dataset/bvi-dvc"> <span class="badge badge-primary"> <img src="https://production-media.paperswithcode.com/tasks/default.gif"> BVI-DVC </span> </a> </li> <li> <a href="/dataset/yt-ugc"> <span class="badge badge-primary"> <img src="https://production-media.paperswithcode.com/thumbnails/dataset/dataset-0000006910-e023e4db.jpg"> YT-UGC </span> </a> </li> <li> <a href="/dataset/vinoground"> <span class="badge badge-primary"> <img src="https://production-media.paperswithcode.com/tasks/default.gif"> Vinoground </span> </a> </li> <li> <a href="/dataset/deep-fakes-dataset"> <span class="badge badge-primary"> <img src="https://production-media.paperswithcode.com/thumbnails/dataset/dataset-0000004135-bbf700d0.jpg"> Deep Fakes Dataset </span> </a> </li> <li> <a href="/dataset/ali"> <span class="badge badge-primary"> <img src="https://production-media.paperswithcode.com/thumbnails/dataset/40ccdc46-58aa-4192-aaee-b1bc1db4b37d.jpg"> SEPE 8K </span> </a> </li> </ul> </div> </div> </div>  <div class="title paper-list" id="code"> <h2 id="papers-list" class="home-page-title">Most implemented papers</h2> <div class="paper-filter-btn"> <div class="btn-group" role="group"> <a data-title="Most implemented papers" data-call-url="/tasklist/video-compression/greatest" data-target="/task/video-compression" class="list-papers-button list-button-active" style="margin-right:0">Most implemented</a> <a data-title="Hot papers on social media" data-call-url="/tasklist/video-compression/social" data-target="/task/video-compression/social" class="list-papers-button list-button" style="margin-right:0">Social</a> <a data-title="Latest papers" data-call-url="/tasklist/video-compression/latest" data-target="/task/video-compression/latest" class="list-papers-button list-button" style="margin-right:0">Latest</a> <a data-title="Latest papers with no code" data-call-url="/tasklist/video-compression/codeless" data-target="/task/video-compression/codeless" class="list-papers-button list-button">No code</a> </div> </div> </div>  <input id="paper-list-search" type="search" class="form-control form-control-sm" placeholder="Search for a paper, author or keyword"> <div class="loading-tab" style="display: none"> <div class="loader-ellips"> <span class="loader-ellips__dot"></span> <span class="loader-ellips__dot"></span> <span class="loader-ellips__dot"></span> <span class="loader-ellips__dot"></span> </div> </div> <div id="task-papers-list"> <div class="infinite-container text-center"> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/dvc-an-end-to-end-deep-video-compression"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/1812.00101.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/dvc-an-end-to-end-deep-video-compression">DVC: An End-to-end Deep Video Compression Framework</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/GuoLusjtu/DVC" onclick="captureOutboundLink('https://github.com/GuoLusjtu/DVC'); return true;" style="font-size:13px"> GuoLusjtu/DVC </a> </span> • <span class="item-framework-link"> <img class="" src="data:image/png;base64,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" /> </span> • <span class="item-conference-link"> <a href="/conference/cvpr-2019-6"> CVPR 2019 </a> </span> </p> <p class="item-strip-abstract">Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 4</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/dvc-an-end-to-end-deep-video-compression" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/dvc-an-end-to-end-deep-video-compression#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/opendvc-an-open-source-implementation-of-the"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/2006.15862.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/opendvc-an-open-source-implementation-of-the">OpenDVC: An Open Source Implementation of the DVC Video Compression Method</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/RenYang-home/OpenDVC" onclick="captureOutboundLink('https://github.com/RenYang-home/OpenDVC'); return true;" style="font-size:13px"> RenYang-home/OpenDVC </a> </span> • <span class="item-framework-link"> <img class="" src="data:image/png;base64,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" /> </span> • <span class="author-name-text item-date-pub">29 Jun 2020</span> </p> <p class="item-strip-abstract">At the time of writing this report, several learned video compression methods are superior to DVC, but currently none of them provides open source codes.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 4</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/opendvc-an-open-source-implementation-of-the" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/opendvc-an-open-source-implementation-of-the#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/compressai-a-pytorch-library-and-evaluation"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/2011.03029.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/compressai-a-pytorch-library-and-evaluation">CompressAI: a PyTorch library and evaluation platform for end-to-end compression research</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/InterDigitalInc/CompressAI" onclick="captureOutboundLink('https://github.com/InterDigitalInc/CompressAI'); return true;" style="font-size:13px"> InterDigitalInc/CompressAI </a> </span> • <span class="item-framework-link"> <img class="" src="https://production-assets.paperswithcode.com/perf/images/frameworks/pytorch-2fbf2cb9.png" /> </span> • <span class="author-name-text item-date-pub">5 Nov 2020</span> </p> <p class="item-strip-abstract">This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 4</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/compressai-a-pytorch-library-and-evaluation" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/compressai-a-pytorch-library-and-evaluation#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/semantic-perceptual-image-compression-using"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/1612.08712.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/semantic-perceptual-image-compression-using">Semantic Perceptual Image Compression using Deep Convolution Networks</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/iamaaditya/image-compression-cnn" onclick="captureOutboundLink('https://github.com/iamaaditya/image-compression-cnn'); return true;" style="font-size:13px"> iamaaditya/image-compression-cnn </a> </span> • <span class="item-framework-link"> <img class="" src="data:image/png;base64,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" /> </span> • <span class="author-name-text item-date-pub">27 Dec 2016</span> </p> <p class="item-strip-abstract">Here, we present a powerful cnn tailored to the specific task of semantic image understanding to achieve higher visual quality in lossy compression.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/semantic-perceptual-image-compression-using" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/semantic-perceptual-image-compression-using#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/disentangled-sequential-autoencoder"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/1803.02991.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/disentangled-sequential-autoencoder">Disentangled Sequential Autoencoder</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/yatindandi/Disentangled-Sequential-Autoencoder" onclick="captureOutboundLink('https://github.com/yatindandi/Disentangled-Sequential-Autoencoder'); return true;" style="font-size:13px"> yatindandi/Disentangled-Sequential-Autoencoder </a> </span> • <span class="item-framework-link"> <img class="" src="https://production-assets.paperswithcode.com/perf/images/frameworks/pytorch-2fbf2cb9.png" /> </span> • <span class="item-conference-link"> <a href="/conference/icml-2018-7"> ICML 2018 </a> </span> </p> <p class="item-strip-abstract">This architecture gives us partial control over generating content and dynamics by conditioning on either one of these sets of features.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/disentangled-sequential-autoencoder" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/disentangled-sequential-autoencoder#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/learning-for-video-compression-with"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/2003.01966.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/learning-for-video-compression-with">Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/RenYang-home/HLVC" onclick="captureOutboundLink('https://github.com/RenYang-home/HLVC'); return true;" style="font-size:13px"> RenYang-home/HLVC </a> </span> • <span class="item-framework-link"> <img class="" src="data:image/png;base64,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" /> </span> • <span class="item-conference-link"> <a href="/conference/cvpr-2020-6"> CVPR 2020 </a> </span> </p> <p class="item-strip-abstract">In our HLVC approach, the hierarchical quality benefits the coding efficiency, since the high quality information facilitates the compression and enhancement of low quality frames at encoder and decoder sides, respectively.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/learning-for-video-compression-with" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/learning-for-video-compression-with#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/hierarchical-autoregressive-modeling-for-1"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/2010.10258.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/hierarchical-autoregressive-modeling-for-1">Hierarchical Autoregressive Modeling for Neural Video Compression</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/buggyyang/youtube-nt" onclick="captureOutboundLink('https://github.com/buggyyang/youtube-nt'); return true;" style="font-size:13px"> buggyyang/youtube-nt </a> </span> • <span class="item-conference-link"> <a href="/conference/iclr-2021-1"> ICLR 2021 </a> </span> </p> <p class="item-strip-abstract">Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/hierarchical-autoregressive-modeling-for-1" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/hierarchical-autoregressive-modeling-for-1#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/perceptual-video-compression-with-recurrent"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/2109.03082.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/perceptual-video-compression-with-recurrent">Perceptual Learned Video Compression with Recurrent Conditional GAN</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/renyang-home/plvc" onclick="captureOutboundLink('https://github.com/renyang-home/plvc'); return true;" style="font-size:13px"> renyang-home/plvc </a> </span> • <span class="item-framework-link"> <img class="" src="data:image/png;base64,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" /> </span> • <span class="author-name-text item-date-pub">7 Sep 2021</span> </p> <p class="item-strip-abstract">This paper proposes a Perceptual Learned Video Compression (PLVC) approach with recurrent conditional GAN.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/perceptual-video-compression-with-recurrent" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/perceptual-video-compression-with-recurrent#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/transformer-based-transform-coding"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/882962.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/transformer-based-transform-coding">Transformer-based Transform Coding</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/Nikolai10/SwinT-ChARM" onclick="captureOutboundLink('https://github.com/Nikolai10/SwinT-ChARM'); return true;" style="font-size:13px"> Nikolai10/SwinT-ChARM </a> </span> • <span class="item-framework-link"> <img class="" src="data:image/png;base64,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" /> </span> • <span class="item-conference-link"> <a href="/conference/iclr-2022-4"> ICLR 2022 </a> </span> </p> <p class="item-strip-abstract">Neural data compression based on nonlinear transform coding has made great progress over the last few years, mainly due to improvements in prior models, quantization methods and nonlinear transforms.</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/transformer-based-transform-coding" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/transformer-based-transform-coding#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> <div class="paper-card infinite-item">  <div class="container-fluid"> <div class="row"> <div class="col-lg-3"> <a href="/paper/nerv-neural-representations-for-videos"> <div class="item-image" style="background-image: url('https://production-media.paperswithcode.com/thumbnails/paper/2110.13903.jpg');"> </div> </a> </div> <div class="col-lg-9"> <div class="row"> <div class="col-lg-9 item-content"> <h1><a href="/paper/nerv-neural-representations-for-videos">NeRV: Neural Representations for Videos</a></h1> <p class="author-section" style="padding-top:2px"> <span class="item-github-link"> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> <a href="https://github.com/haochen-rye/nerv" onclick="captureOutboundLink('https://github.com/haochen-rye/nerv'); return true;" style="font-size:13px"> haochen-rye/nerv </a> </span> • <span class="item-framework-link"> <img class="" src="https://production-assets.paperswithcode.com/perf/images/frameworks/pytorch-2fbf2cb9.png" /> </span> • <span class="item-conference-link"> <a href="/conference/neurips-2021-12"> NeurIPS 2021 </a> </span> </p> <p class="item-strip-abstract">In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H. 264, HEVC \etc).</p> </div> <div class="col-lg-3 item-interact text-center"> <div class="entity-stars"> <span class="badge badge-secondary"><span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> 3</span> </div> <div class="entity" style="margin-bottom: 20px;"> <a href="/paper/nerv-neural-representations-for-videos" class="badge badge-light "> <span class=" icon-wrapper icon-ion" data-name="document"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M428 224H288a48 48 0 0 1-48-48V36a4 4 0 0 0-4-4h-92a64 64 0 0 0-64 64v320a64 64 0 0 0 64 64h224a64 64 0 0 0 64-64V228a4 4 0 0 0-4-4z"/><path d="M419.22 188.59L275.41 44.78a2 2 0 0 0-3.41 1.41V176a16 16 0 0 0 16 16h129.81a2 2 0 0 0 1.41-3.41z"/></svg></span> Paper </a> <br/> <a href="/paper/nerv-neural-representations-for-videos#code" class="badge badge-dark "> <span class=" icon-wrapper icon-ion" data-name="logo-github"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M256 32C132.3 32 32 134.9 32 261.7c0 101.5 64.2 187.5 153.2 217.9a17.56 17.56 0 0 0 3.8.4c8.3 0 11.5-6.1 11.5-11.4 0-5.5-.2-19.9-.3-39.1a102.4 102.4 0 0 1-22.6 2.7c-43.1 0-52.9-33.5-52.9-33.5-10.2-26.5-24.9-33.6-24.9-33.6-19.5-13.7-.1-14.1 1.4-14.1h.1c22.5 2 34.3 23.8 34.3 23.8 11.2 19.6 26.2 25.1 39.6 25.1a63 63 0 0 0 25.6-6c2-14.8 7.8-24.9 14.2-30.7-49.7-5.8-102-25.5-102-113.5 0-25.1 8.7-45.6 23-61.6-2.3-5.8-10-29.2 2.2-60.8a18.64 18.64 0 0 1 5-.5c8.1 0 26.4 3.1 56.6 24.1a208.21 208.21 0 0 1 112.2 0c30.2-21 48.5-24.1 56.6-24.1a18.64 18.64 0 0 1 5 .5c12.2 31.6 4.5 55 2.2 60.8 14.3 16.1 23 36.6 23 61.6 0 88.2-52.4 107.6-102.3 113.3 8 7.1 15.2 21.1 15.2 42.5 0 30.7-.3 55.5-.3 63 0 5.4 3.1 11.5 11.4 11.5a19.35 19.35 0 0 0 4-.4C415.9 449.2 480 363.1 480 261.7 480 134.9 379.7 32 256 32z"/></svg></span> Code </a> <br/> </div> </div> </div> </div> </div> </div> </div> </div> <div class="loading" style="display: none"> <div class="loader-ellips infinite-scroll-request"> <span class="loader-ellips__dot"></span> <span class="loader-ellips__dot"></span> <span class="loader-ellips__dot"></span> <span class="loader-ellips__dot"></span> </div> </div> <a class="infinite-more-link" href="?page=2&q="></a> </div> <div class="loading-trigger"></div> </div> <div class="col-lg-3 wide-sidebar task-infobox" id="task-sidebar"> <div class="image-container"> <a href="https://production-media.paperswithcode.com/thumbnails/task/task-0000000733-7b89a5de.jpg" data-lightbox="imageresource"> <img id="imageresource" width=100% src="https://production-media.paperswithcode.com/thumbnails/task/task-0000000733-7b89a5de.jpg"> </a> </div> <div class="task-toc"> <h4>Content</h4> <hr> <nav> <a class="toc-link" href="#task-home"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="book"><svg viewBox="0 0 448 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M356 161H188c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12v8c0 6.6-5.4 12-12 12zm12 52c0 6.6-5.4 12-12 12H188c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12v8zm64.7 268h3.3c6.6 0 12 5.4 12 12v8c0 6.6-5.4 12-12 12H80c-44.2 0-80-35.8-80-80V81C0 36.8 35.8 1 80 1h344c13.3 0 24 10.7 24 24v368c0 10-6.2 18.6-14.9 22.2-3.6 16.1-4.4 45.6-.4 65.8zM128 385h288V33H128v352zm-96 16c13.4-10 30-16 48-16h16V33H80c-26.5 0-48 21.5-48 48v320zm372.3 80c-3.1-20.4-2.9-45.2 0-64H80c-64 0-64 64 0 64h324.3z"/></svg></span> Introduction</a> <a class="toc-link" href="#benchmarks"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="chart-line"><svg viewBox="0 0 512 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M504 417c4.42 0 8 3.58 8 8v16c0 4.42-3.58 8-8 8H16c-8.84 0-16-7.16-16-16V73c0-4.42 3.58-8 8-8h16c4.42 0 8 3.58 8 8v344h472zM98.34 264.03l84.12-83.32c6.25-6.2 16.34-6.18 22.57.05l84.63 84.63 82.22-82.22-44.71-44.71C311.87 123.16 322.7 97 344.34 97h119.47c8.94 0 16.19 7.25 16.19 16.19v119.47c0 14.64-11.98 24.34-24.46 24.34-5.97 0-12.05-2.21-17-7.16L394.5 205.8l-93.53 93.53c-6.25 6.25-16.38 6.25-22.63 0l-84.69-84.69-72.69 72.01c-3.12 3.12-8.19 3.12-11.31 0l-11.31-11.31c-3.12-3.12-3.12-8.19 0-11.31zM362.96 129L448 214.04V129h-85.04z"/></svg></span> Benchmarks</a> <a class="toc-link" href="#datasets"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="database"><svg viewBox="0 0 448 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M224 33C118 33 32 61.75 32 97v32c0 35.25 86 64 192 64s192-28.75 192-64V97c0-35.25-86-64-192-64zm192 149.5c-41.251 29-116.75 42.5-192 42.5S73.25 211.5 32 182.5V225c0 35.25 86 64 192 64s192-28.75 192-64v-42.5zm0 96c-41.251 29-116.75 42.5-192 42.5S73.25 307.5 32 278.5V321c0 35.25 86 64 192 64s192-28.75 192-64v-42.5zm0 96c-41.251 29-116.75 42.5-192 42.5S73.25 403.5 32 374.5V417c0 35.25 86 64 192 64s192-28.75 192-64v-42.5zM224 1c77.904 0 224 18.662 224 96v320c0 77.2-145.858 96-224 96-77.904 0-224-18.662-224-96V97C0 19.8 145.858 1 224 1z"/></svg></span> Datasets</a> <a class="toc-link" href="#task-libraries"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="file-code"><svg viewBox="0 0 384 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M369.941 98.941c7.76 7.76 14.059 22.966 14.059 33.94V465c0 26.51-21.49 48-48 48H48c-26.51 0-48-21.49-48-48V49C0 22.49 21.49 1 48 1h204.118c10.975 0 26.18 6.3 33.94 14.059zm-22.627 22.628l-83.883-83.884c-1.728-1.73-5.057-3.608-7.431-4.194V129h95.509c-.586-2.374-2.465-5.703-4.195-7.431zM336 481c8.837 0 16-7.163 16-16V161H248c-13.254 0-24-10.745-24-24V33H48c-8.836 0-16 7.163-16 16v416c0 8.837 7.164 16 16 16h288zm-161.47-67.404l-25.93-7.527c-2.03-.59-3.677-2.784-3.677-4.898 0-.4.09-1.037.202-1.422l58.027-199.869c.59-2.03 2.784-3.678 4.898-3.678.4 0 1.038.09 1.422.202l25.928 7.527c2.03.59 3.677 2.784 3.677 4.898 0 .4-.09 1.037-.202 1.422l-58.026 199.87c-.59 2.03-2.784 3.677-4.898 3.677-.4 0-1.037-.09-1.422-.202zm-48.447-47.674c-.834.89-2.5 1.612-3.72 1.612-1.115 0-2.677-.618-3.49-1.38L57.611 308.72c-.89-.834-1.613-2.501-1.613-3.721 0-1.219.723-2.886 1.613-3.72l61.262-57.434c.813-.761 2.375-1.38 3.489-1.38 1.22 0 2.886.723 3.72 1.613l18.493 19.724c.761.812 1.38 2.375 1.38 3.488 0 1.273-.776 2.988-1.732 3.83L105.725 305l38.5 33.88c.954.842 1.73 2.557 1.73 3.83 0 1.113-.619 2.676-1.38 3.488zm139.043.232c-.812.762-2.375 1.38-3.488 1.38-1.22 0-2.887-.722-3.72-1.612l-18.493-19.724c-.762-.812-1.38-2.375-1.38-3.488 0-1.273.776-2.988 1.732-3.83L278.276 305l-38.5-33.88c-.954-.842-1.73-2.557-1.73-3.83 0-1.113.619-2.676 1.38-3.488l18.491-19.724c.834-.89 2.501-1.612 3.721-1.612 1.113 0 2.676.618 3.488 1.379l61.262 57.434c.89.834 1.612 2.501 1.612 3.72 0 1.22-.722 2.887-1.612 3.72z"/></svg></span> Libraries</a> <a class="toc-link" href="#papers-list"><span class=" icon-wrapper icon-fa icon-fa-light" data-name="file"><svg viewBox="0 0 384 520.146" xmlns="http://www.w3.org/2000/svg"><path d="M369.9 98.9c9 9 14.1 21.3 14.1 34V465c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V49C0 22.5 21.5 1 48 .9h204.1C264.8.9 277 6 286 15zm-22.6 22.7l-83.899-83.9c-2.1-2.1-4.6-3.5-7.4-4.2V129h95.5c-.7-2.8-2.1-5.3-4.2-7.4zM336 481c8.8 0 16-7.2 16-16V161H248c-13.3 0-24-10.7-24-24V33H48c-8.8 0-16 7.2-16 16v416c0 8.8 7.2 16 16 16h288z"/></svg></span> Papers</a> <a data-call-url="/tasklist/video-compression/greatest" data-target="/task/video-compression" class="toc-papers-button" style="padding-left: 16px;" href="#papers-list">- Most implemented</a> <a data-call-url="/tasklist/video-compression/social" data-target="/task/video-compression/social" class="toc-papers-button" style="padding-left: 16px;" href="#papers-list">- Social</a> <a data-call-url="/tasklist/video-compression/latest" data-target="/task/video-compression/latest" class="toc-papers-button" style="padding-left: 16px;" href="#papers-list">- Latest</a> <a data-call-url="/tasklist/video-compression/codeless" data-target="/task/video-compression/codeless" class="toc-papers-button" style="padding-left: 16px;" href="#papers-list">- No code</a> </nav> </div> </div> </main> </div> <div class="footer"> <div class="footer-contact"> <span class="footer-contact-item">Contact us on:</span> <a class="footer-contact-item" href="mailto:hello@paperswithcode.com"> <span class=" icon-wrapper icon-ion" data-name="mail"><svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512"><path d="M424 80H88a56.06 56.06 0 0 0-56 56v240a56.06 56.06 0 0 0 56 56h336a56.06 56.06 0 0 0 56-56V136a56.06 56.06 0 0 0-56-56zm-14.18 92.63l-144 112a16 16 0 0 1-19.64 0l-144-112a16 16 0 1 1 19.64-25.26L256 251.73l134.18-104.36a16 16 0 0 1 19.64 25.26z"/></svg></span> hello@paperswithcode.com </a>. <span class="footer-contact-item"> Papers With Code is a free resource with all data licensed under <a rel="noreferrer" href="https://creativecommons.org/licenses/by-sa/4.0/">CC-BY-SA</a>. </span> </div> <div class="footer-links"> <a href="/site/terms">Terms</a> <a href="/site/data-policy">Data policy</a> <a href="/site/cookies-policy">Cookies policy</a> <a href="/about#team" class="fair-logo"> from <img src="data:image/png;base64,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"> </a> </div> </div> <script> // MathJax window.MathJax = { tex: { inlineMath: [ ["$", "$"], ["\$", "\$"], ], }, }; const mathjaxScript = document.createElement("script"); mathjaxScript.src = "https://production-assets.paperswithcode.com/static/js/mathjax/tex-chtml.js"; document.head.appendChild(mathjaxScript); </script> <script src="https://production-assets.paperswithcode.com/perf/766.4af6b88b.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/2.6da00df7.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/351.a22a9607.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/101.5f271f23.js" defer></script><script src="https://production-assets.paperswithcode.com/perf/view_task.e61ab167.js" defer></script> </body> </html>

CINXE.COM

Video Compression | Papers With Code