CINXE.COM

<!DOCTYPE html> <html lang="en-US"> <head> <meta charset="UTF-8">  <title>Synthetic Data for Computer Vision - CVPR 2025 | Synthetic Data for Computer Vision</title> <meta name="generator" content="Jekyll v3.10.0" /> <meta property="og:title" content="Synthetic Data for Computer Vision - CVPR 2025" /> <meta property="og:locale" content="en_US" /> <meta name="description" content="[“CVPR 2025 Workshop”, “June, 2025”, “Nashville, TN, United States”]" /> <meta property="og:description" content="[“CVPR 2025 Workshop”, “June, 2025”, “Nashville, TN, United States”]" /> <link rel="canonical" href="https://syndata4cv.github.io/" /> <meta property="og:url" content="https://syndata4cv.github.io/" /> <meta property="og:site_name" content="Synthetic Data for Computer Vision" /> <meta property="og:type" content="website" /> <meta name="twitter:card" content="summary" /> <meta property="twitter:title" content="Synthetic Data for Computer Vision - CVPR 2025" /> <script type="application/ld+json"> {"@context":"https://schema.org","@type":"WebSite","description":"[“CVPR 2025 Workshop”, “June, 2025”, “Nashville, TN, United States”]","headline":"Synthetic Data for Computer Vision - CVPR 2025","name":"Synthetic Data for Computer Vision","url":"https://syndata4cv.github.io/"}</script>  <meta property="og:title" content='SynData4CV-CVPR'/> <meta property="og:image" content="syndata4cv.github.io/pics/seattle_view.jpg"> <meta property="og:image:type" content="image/jpeg"> <meta property="og:image:width" content="200"> <meta property="og:image:height" content="200"> <meta property="og:type" content='website'/> <meta name="description" content="CVPR 2025 WorkshopJune, 2025Nashville, TN, United States"/> <meta name="viewport" content="width=device-width, initial-scale=1"> <meta name="theme-color" content="#39275B"> <link href='https://fonts.googleapis.com/css?family=Open+Sans:400,700' rel='stylesheet' type='text/css'> <link rel="stylesheet" href="/assets/css/style.css?v=2f677d3a9062476a34cd4977d4c73ff4e64b3f86">  <nav> <ul> <li><a href="/">CVPR 2025 Workshop</a></li> <li><a href="/cvpr2024.html">CVPR 2024 Workshop (Previous)</a></li> </ul> </nav> <style> nav ul { list-style: none; /* Remove bullets */ padding: 0; margin: 0; display: flex; /* Arrange items in a row */ justify-content: center; /* Center the navigation bar */ } nav ul li { margin: 0 10px; /* Add some spacing between items */ } nav ul li a { text-decoration: none; /* Remove underline */ color: #000; /* Change color as needed */ font-weight: bold; /* Make text bold */ font-size: 18px; /* Adjust size as needed */ transition: color 0.2s; } nav ul li a:hover { color: #39275B; /* Hover effect color */ } </style> </head> <body> <style> .logo { display: block; margin-left: auto; margin-right: auto; width: 50%; background-color: #000000; } .page-header1 { background-repeat: no-repeat; background-size: 100%; background-position: center; padding-bottom: 1rem; background-color: #ffffff; background-image: url('pics/nashvile_view.jpg'); } .page-header2 { background-color: #ffffff; background-image: linear-gradient(120deg, #ffffff, #ffffff); } .btn { display: inline-block; margin-bottom: 1rem; color: rgba(0, 0, 0, 0.897); background-color: rgba(0, 0, 0, 0.8); border-color: rgba(0, 0, 0, 0.918); border-style: solid; border-width: 1px; border-radius: 0.3rem; transition: color 0.2s, background-color 0.2s, border-color 0.2s; } </style> <section class="page-header page-header1">  <h1 class="project-name" style="color:#ffffff; ">Synthetic Data for Computer Vision - CVPR 2025</h1> <h2 class="project-tagline" style="font-size: 32px; color:#ffffff ; opacity: 100%; "><span>CVPR 2025 Workshop</span><br><span>June, 2025</span><br><span>Nashville, TN, United States</span><br></h2> <br> <br> <br> <br> <br> <br> <a href="./index.html" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Overview</a> <a href="./index.html#invited-speakers" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Invited Speakers</a> <a href="./index.html#schedule" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Schedule</a> <a href="./index.html#call-for-papers" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Call for Papers</a> <a href="index.html#sponsorship" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Sponsorship</a> <a href="./index.html#important-workshop-dates" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Important Dates</a> <a href="./index.html#related-workshops" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Related Workshops</a> <a href="./index.html#organizers" class="btn" style="color:#ffffff ; font-size: large; text-shadow: -0.1px -0.1px 0 #000000, 0.1px -0.1px 0 #000000, -0.1px 0.1px 0 #000000, 0.1px 0.1px 0 #000000;">Organizers</a> </section> <section class="main-content"> <style> .center { display: block; margin-left: auto; margin-right: auto; width: 75%; } </style> <h1 id="overview">Overview</h1> <div style="text-align: left; max-width: 800px; margin: auto;"> The workshop aims to explore the use of synthetic data in training and evaluating computer vision models, as well as in other related domains. During the last decade, advancements in computer vision were catalyzed by the release of painstakingly curated human-labeled datasets. Recently, people have increasingly resorted to synthetic data as an alternative to laborintensive human-labeled datasets for its scalability, customizability, and costeffectiveness. Synthetic data offers the potential to generate large volumes of diverse and high-quality vision data, tailored to specific scenarios and edge cases that are hard to capture in real-world data. However, challenges such as the domain gap between synthetic and real-world data, potential biases in synthetic generation, and ensuring the generalizability of models trained on synthetic data remain. We hope the workshop can provide a forum to discuss and encourage further exploration in these areas. </div> <h1 id="invited-speakers">Invited Speakers</h1> <ul> <li>The speakers haven’t been finalized, stay tuned for updates!</li> </ul> <div style="display: flex; flex-wrap: wrap; justify-content: space-around;"> <div style="width:45%; margin: 1%;"> <a href="https://anikem.github.io/"> <img alt="Angela Dai" src="pics/speakers/dai.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover; " /> </a><br /> <a href="https://www.3dunderstanding.org/">Angela Dai</a><br /> Technical University of Munich </div> <div style="width:45%; margin: 1%;"> <a href="https://groups.csail.mit.edu/vision/torralbalab/"> <img alt="Antonio Torralba" src="pics/speakers/antonio.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover; " /> </a><br /> <a href="https://groups.csail.mit.edu/vision/torralbalab/">Antonio Torralba</a><br /> Massachusetts Institute of Technology </div> <div style="width:45%; margin: 1%;"> <a href="https://www.cs.cornell.edu/~bharathh/"> <img alt="Bharath Hariharan" src="pics/speakers/bharath.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover; " /> </a><br /> <a href="https://www.cs.cornell.edu/~bharathh/">Bharath Hariharan</a><br /> Cornell University </div> <div style="width:45%; margin: 1%;"> <a href="https://boleizhou.github.io/"> <img alt="Ming Lin" src="pics/speakers/bolei.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover; " /> </a><br /> <a href="https://boleizhou.github.io/">Bolei Zhou</a><br /> University of California, Los Angeles </div> <div style="width:45%; margin: 1%;"> <a href="https://www.cs.princeton.edu/~jiadeng/"> <img alt="Jia Deng" src="pics/speakers/jiadeng.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover; " /> </a><br /> <a href="https://www.cs.princeton.edu/~jiadeng/"> Jia Deng</a><br /> Princeton University </div> <div style="width:45%; margin: 1%;"> <a href="https://kianaehsani.com/"> <img alt="Kiana Ehsani" src="pics/speakers/kiana.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover; " /> </a><br /> <a href="https://kianaehsani.com/">Kiana Ehsani</a><br /> Vercept </div> <div style="width:45%; margin: 1%;"> <a href=""> </a><br /> <a href=""></a><br /> </div> </div> <h1 id="schedule">Schedule</h1> <ul> <li>Stay tuned for updates!</li> </ul> <h1 id="poster-session">Poster Session</h1> <ul> <li>Stay tuned for updates!</li> </ul> <h1 id="awards">Awards</h1> <ul> <li>Stay tuned for updates!</li> </ul> <h1 id="sponsorship">Sponsorship</h1> <ul> <li>If you are interested in sponsoring SynData4CV workshop @ CVPR 2025, please reach out to Jieyu Zhang (jieyuz2@cs.washington.edu).</li> </ul>         <h1 id="call-for-papers">Call for Papers</h1> <p>We invite papers on <strong>the use of synthetic data for training and evaluating computer vision models.</strong> We welcome submissions along two tracks:</p> <ul> <li> <p><strong>Full papers:</strong> Up to 8 pages, not including references/appendix.</p> </li> <li> <p><strong>Short papers:</strong> Up to 4 pages, not including references/appendix.</p> </li> </ul> <p>Accepted papers will be allocated a poster presentation and displayed on the workshop website. In addition, we will offer a Best Long Paper award, Best Paper Runner-up award, and Best Short Paper with oral presentation.</p> <h3 id="topics">Topics</h3> <p>Potential topics include, but are not limited to:</p> <ul> <li> <p><strong>Effectiveness:</strong> What is the most effective way to generate and leverage synthetic data? How "realistic" does synthetic data need to be?</p> </li> <li> <p><strong>Efficiency and scalability:</strong> Can we make synthetic data generation more efficient and scalable without sacrificing quality?</p> </li> <li> <p><strong>Benchmark and evaluation:</strong> What benchmark and evaluation methods are needed to assess the efficacy of synthetic data for computer vision?</p> </li> <li> <p><strong>Risks and ethical considerations:</strong> What ethical questions and risks are associated with synthetic data (<em>e.g.</em> bias amplification), and how can we address them?</p> </li> <li> <p><strong>Applications:</strong> In addition to existing attempts on leveraging synthetic data for training visual recognition and vision-language models, what are other tasks in computer vision or other related fields (<em>e.g.</em>, robotics, NLP) that could benefit from synthetic data?</p> </li> <li> <p><strong>Other open problems:</strong> How do we decide which type of data to use, synthetic or real-world data? What is the optimal way to combine both if both are available? How much real-world data do we need (in the long run)?</p> </li> </ul> <h3 id="submission-instructions">Submission Instructions</h3> <p>Submissions should be anonymized and formatted using the <a href="https://github.com/cvpr-org/author-kit/releases">CVPR 2025 template</a> and uploaded as a single PDF. Note that our workshop is non-archival.<br /> <br /> <strong>Submission link:</strong> <a href="https://openreview.net/group?id=thecvf.com/CVPR/2025/Workshop/SynData4CV">OpenReview Link</a></p> <h1 id="important-workshop-dates">Important workshop dates</h1>  <ul> <li>Deadline for submission: <strong>March 31th, 11:59 PM Pacific Time</strong></li> <li>Notification of acceptance: <strong>April 9th, 11:59 PM Pacific Time (Tentative)</strong></li> <li>Camera Ready submission deadline: <strong>April 24th, 11:59 PM Pacific Time (Tentative)</strong></li> <li>Workshop date: <strong>June 11th, 2025 (Full day) (Tentative)</strong></li> </ul>    <h1 id="related-workshops">Related Workshops</h1> <ul> <li><a href="https://syntml-cvpr2022-workshop.github.io/">Machine Learning with Synthetic Data @ CVPR 2022</a></li> <li><a href="https://sites.google.com/view/sdas2023/">Synthetic Data for Autonomous Systems @ CVPR 2023</a></li> <li><a href="https://www.syntheticdata4ml.vanderschaar-lab.com/">Synthetic Data Generation with Generative AI @ NeurIPS 2023</a></li> </ul> <h1 id="organizers">Organizers</h1> <div style="display: flex; flex-wrap: wrap; justify-content: space-around;">  <div style="width:45%; margin: 1%;"> <a href="https://jieyuz2.github.io/"> <img alt="Jieyu Zhang" src="pics/organizers/jieyuzhang.png" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://jieyuz2.github.io/">Jieyu Zhang</a><br /> University of Washington </div>  <div style="width:45%; margin: 1%;"> <a href="https://weikaih2004.github.io/"> <img alt="Weikai Huang" src="pics/organizers/weikaihuang.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://weikaih2004.github.io/">Weikai Huang</a><br /> University of Washington </div>  <div style="width:45%; margin: 1%;"> <a href="https://chengyuhsieh.github.io/"> <img alt="Cheng-Yu Hsieh" src="pics/organizers/chengyuhsieh.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://chengyuhsieh.github.io/">Cheng-Yu Hsieh</a><br /> University of Washington </div>  <div style="width:45%; margin: 1%;"> <a href="https://zixianma.github.io/"> <img alt="Zixian Ma" src="pics/organizers/zixianma.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://zixianma.github.io/">Zixian Ma</a><br /> University of Washington </div>  <div style="width:45%; margin: 1%;"> <a href="https://red-fairy.github.io/"> <img alt="Rundong Luo" src="pics/organizers/rundongluo.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://red-fairy.github.io/">Rundong Luo</a><br /> Cornell University </div>  <div style="width:45%; margin: 1%;"> <a href="https://ssundaram21.github.io/"> <img alt="Shobhita Sundaram" src="pics/organizers/ssundaram.png" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://ssundaram21.github.io/">Shobhita Sundaram</a><br /> Massachusetts Institute of Technology </div>  <div style="width:45%; margin: 1%;"> <a href="https://people.csail.mit.edu/weichium/"> <img alt="Wei-Chiu Ma" src="pics/organizers/weichiuma.png" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://people.csail.mit.edu/weichium/">Wei-Chiu Ma</a><br /> Cornell University </div>  <div style="width:45%; margin: 1%;"> <a href="https://ranjaykrishna.com/index.html"> <img alt="Ranjay Krishna" src="pics/organizers/ranjaykrishna.jpg" height="200" width="200" style="border-radius: 50%; object-fit: cover;" /> </a><br /> <a href="https://ranjaykrishna.com/index.html">Ranjay Krishna</a><br /> University of Washington </div> </div> <footer class="site-footer"> </footer> </section> </body> </html>