Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–12 of 12 results for author: <span class="mathjax">Gonzalez-Franco, M</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Gonzalez-Franco%2C+M">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Gonzalez-Franco, M"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Gonzalez-Franco%2C+M&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Gonzalez-Franco, M"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.12681">arXiv:2412.12681</a> <span> [<a href="https://arxiv.org/pdf/2412.12681">pdf</a>, <a href="https://arxiv.org/format/2412.12681">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3706599.3706741">10.1145/3706599.3706741 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Everyday AR through AI-in-the-Loop </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Suzuki%2C+R">Ryo Suzuki</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=Sra%2C+M">Misha Sra</a>, <a href="/search/cs?searchtype=author&query=Lindlbauer%2C+D">David Lindlbauer</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.12681v1-abstract-short" style="display: inline;"> This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR -- always-available and seamlessly integrated into users' daily environments -- is becoming increasingly feasible. This works… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12681v1-abstract-full').style.display = 'inline'; document.getElementById('2412.12681v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.12681v1-abstract-full" style="display: none;"> This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR -- always-available and seamlessly integrated into users' daily environments -- is becoming increasingly feasible. This workshop will explore how AI can drive such everyday AR experiences. We discuss a range of topics, including adaptive and context-aware AR, generative AR content creation, always-on AI assistants, AI-driven accessible design, and real-world-oriented AI agents. Our goal is to identify the opportunities and challenges in AI-enabled AR, focusing on creating novel AR experiences that seamlessly blend the digital and physical worlds. Through the workshop, we aim to foster collaboration, inspire future research, and build a community to advance the research field of AI-enhanced AR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12681v1-abstract-full').style.display = 'none'; document.getElementById('2412.12681v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CHI 2025 Extended Abstract</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.08158">arXiv:2408.08158</a> <span> [<a href="https://arxiv.org/pdf/2408.08158">pdf</a>, <a href="https://arxiv.org/format/2408.08158">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> EmBARDiment: an Embodied AI Agent for Productivity in XR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bovo%2C+R">Riccardo Bovo</a>, <a href="/search/cs?searchtype=author&query=Abreu%2C+S">Steven Abreu</a>, <a href="/search/cs?searchtype=author&query=Ahuja%2C+K">Karan Ahuja</a>, <a href="/search/cs?searchtype=author&query=Gonzalez%2C+E+J">Eric J Gonzalez</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+L">Li-Te Cheng</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.08158v1-abstract-short" style="display: inline;"> XR devices running chat-bots powered by Large Language Models (LLMs) have tremendous potential as always-on agents that can enable much better productivity scenarios. However, screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08158v1-abstract-full').style.display = 'inline'; document.getElementById('2408.08158v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.08158v1-abstract-full" style="display: none;"> XR devices running chat-bots powered by Large Language Models (LLMs) have tremendous potential as always-on agents that can enable much better productivity scenarios. However, screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi-modal data dropped as part of the query. We propose a solution that leverages an attention framework that derives context implicitly from user actions, eye-gaze, and contextual memory within the XR environment. This minimizes the need for engineered explicit prompts, fostering grounded and intuitive interactions that glean user insights for the chat-bot. Our user studies demonstrate the imminent feasibility and transformative potential of our approach to streamline user interaction in XR with chat-bots, while offering insights for the design of future XR-embodied LLM agents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08158v1-abstract-full').style.display = 'none'; document.getElementById('2408.08158v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.18207">arXiv:2407.18207</a> <span> [<a href="https://arxiv.org/pdf/2407.18207">pdf</a>, <a href="https://arxiv.org/format/2407.18207">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Geometry Fidelity for Spherical Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Christensen%2C+A">Anders Christensen</a>, <a href="/search/cs?searchtype=author&query=Mojab%2C+N">Nooshin Mojab</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+K">Khushman Patel</a>, <a href="/search/cs?searchtype=author&query=Ahuja%2C+K">Karan Ahuja</a>, <a href="/search/cs?searchtype=author&query=Akata%2C+Z">Zeynep Akata</a>, <a href="/search/cs?searchtype=author&query=Winther%2C+O">Ole Winther</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=Colaco%2C+A">Andrea Colaco</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.18207v1-abstract-short" style="display: inline;"> Spherical or omni-directional images offer an immersive visual format appealing to a wide range of computer vision applications. However, geometric properties of spherical images pose a major challenge for models and metrics designed for ordinary 2D images. Here, we show that direct application of Fr茅chet Inception Distance (FID) is insufficient for quantifying geometric fidelity in spherical imag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18207v1-abstract-full').style.display = 'inline'; document.getElementById('2407.18207v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.18207v1-abstract-full" style="display: none;"> Spherical or omni-directional images offer an immersive visual format appealing to a wide range of computer vision applications. However, geometric properties of spherical images pose a major challenge for models and metrics designed for ordinary 2D images. Here, we show that direct application of Fr茅chet Inception Distance (FID) is insufficient for quantifying geometric fidelity in spherical images. We introduce two quantitative metrics accounting for geometric constraints, namely Omnidirectional FID (OmniFID) and Discontinuity Score (DS). OmniFID is an extension of FID tailored to additionally capture field-of-view requirements of the spherical format by leveraging cubemap projections. DS is a kernel-based seam alignment score of continuity across borders of 2D representations of spherical images. In experiments, OmniFID and DS quantify geometry fidelity issues that are undetected by FID. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.18207v1-abstract-full').style.display = 'none'; document.getElementById('2407.18207v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ECCV 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.09503">arXiv:2407.09503</a> <span> [<a href="https://arxiv.org/pdf/2407.09503">pdf</a>, <a href="https://arxiv.org/format/2407.09503">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Abreu%2C+S">Steven Abreu</a>, <a href="/search/cs?searchtype=author&query=Do%2C+T+D">Tiffany D. Do</a>, <a href="/search/cs?searchtype=author&query=Ahuja%2C+K">Karan Ahuja</a>, <a href="/search/cs?searchtype=author&query=Gonzalez%2C+E+J">Eric J. Gonzalez</a>, <a href="/search/cs?searchtype=author&query=Payne%2C+L">Lee Payne</a>, <a href="/search/cs?searchtype=author&query=McDuff%2C+D">Daniel McDuff</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.09503v2-abstract-short" style="display: inline;"> Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09503v2-abstract-full').style.display = 'inline'; document.getElementById('2407.09503v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.09503v2-abstract-full" style="display: none;"> Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and evaluating these annotations. First, we used a prompt-engineered large language model (LLM) to generate context-aware action suggestions and identified over 18,000 action suggestions. While these synthetic action suggestions are valuable, the inherent limitations of LLMs necessitate human evaluation. To ensure high-quality and user-centered recommendations, we conducted a large-scale human annotation study that provides grounding in human preferences for all of PARSE-Ego4D. We analyze the inter-rater agreement and evaluate subjective preferences of participants. Based on our synthetic dataset and complete human annotations, we propose several new tasks for action suggestions based on ego-centric videos. We encourage novel solutions that improve latency and energy requirements. The annotations in PARSE-Ego4D will support researchers and developers who are working on building action recommendation systems for augmented and virtual reality systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09503v2-abstract-full').style.display = 'none'; document.getElementById('2407.09503v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.09579">arXiv:2406.09579</a> <span> [<a href="https://arxiv.org/pdf/2406.09579">pdf</a>, <a href="https://arxiv.org/format/2406.09579">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Hovering Over the Key to Text Input in XR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=Abdlkarim%2C+D">Diar Abdlkarim</a>, <a href="/search/cs?searchtype=author&query=Bhatia%2C+A">Arpit Bhatia</a>, <a href="/search/cs?searchtype=author&query=Macgregor%2C+S">Stuart Macgregor</a>, <a href="/search/cs?searchtype=author&query=Fotso-Puepi%2C+J+A">Jason Alexander Fotso-Puepi</a>, <a href="/search/cs?searchtype=author&query=Gonzalez%2C+E+J">Eric J Gonzalez</a>, <a href="/search/cs?searchtype=author&query=Seifi%2C+H">Hasti Seifi</a>, <a href="/search/cs?searchtype=author&query=Di+Luca%2C+M">Massimiliano Di Luca</a>, <a href="/search/cs?searchtype=author&query=Ahuja%2C+K">Karan Ahuja</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.09579v1-abstract-short" style="display: inline;"> Virtual, Mixed, and Augmented Reality (XR) technologies hold immense potential for transforming productivity beyond PC. Therefore there is a critical need for improved text input solutions for XR. However, achieving efficient text input in these environments remains a significant challenge. This paper examines the current landscape of XR text input techniques, focusing on the importance of keyboar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09579v1-abstract-full').style.display = 'inline'; document.getElementById('2406.09579v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.09579v1-abstract-full" style="display: none;"> Virtual, Mixed, and Augmented Reality (XR) technologies hold immense potential for transforming productivity beyond PC. Therefore there is a critical need for improved text input solutions for XR. However, achieving efficient text input in these environments remains a significant challenge. This paper examines the current landscape of XR text input techniques, focusing on the importance of keyboards (both physical and virtual) as essential tools. We discuss the unique challenges and opportunities presented by XR, synthesizing key trends from existing solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09579v1-abstract-full').style.display = 'none'; document.getElementById('2406.09579v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.13274">arXiv:2404.13274</a> <span> [<a href="https://arxiv.org/pdf/2404.13274">pdf</a>, <a href="https://arxiv.org/format/2404.13274">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3654777.3676379">10.1145/3654777.3676379 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Augmented Object Intelligence with XR-Objects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Dogan%2C+M+D">Mustafa Doga Dogan</a>, <a href="/search/cs?searchtype=author&query=Gonzalez%2C+E+J">Eric J. Gonzalez</a>, <a href="/search/cs?searchtype=author&query=Ahuja%2C+K">Karan Ahuja</a>, <a href="/search/cs?searchtype=author&query=Du%2C+R">Ruofei Du</a>, <a href="/search/cs?searchtype=author&query=Cola%C3%A7o%2C+A">Andrea Cola莽o</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+J">Johnny Lee</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+D">David Kim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.13274v3-abstract-short" style="display: inline;"> Seamless integration of physical objects as interactive digital entities remains a challenge for spatial computing. This paper explores Artificial Object Intelligence (AOI) in the context of XR, an interaction paradigm that aims to blur the lines between digital and physical by equipping real-world objects with the ability to interact as if they were digital, where every object has the potential t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.13274v3-abstract-full').style.display = 'inline'; document.getElementById('2404.13274v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.13274v3-abstract-full" style="display: none;"> Seamless integration of physical objects as interactive digital entities remains a challenge for spatial computing. This paper explores Artificial Object Intelligence (AOI) in the context of XR, an interaction paradigm that aims to blur the lines between digital and physical by equipping real-world objects with the ability to interact as if they were digital, where every object has the potential to serve as a portal to digital functionalities. Our approach utilizes real-time object segmentation and classification, combined with the power of Multimodal Large Language Models (MLLMs), to facilitate these interactions without the need for object pre-registration. We implement the AOI concept in the form of XR-Objects, an open-source prototype system that provides a platform for users to engage with their physical environment in contextually relevant ways using object-based context menus. This system enables analog objects to not only convey information but also to initiate digital actions, such as querying for details or executing tasks. Our contributions are threefold: (1) we define the AOI concept and detail its advantages over traditional AI assistants, (2) detail the XR-Objects system's open-source design and implementation, and (3) show its versatility through various use cases and a user study. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.13274v3-abstract-full').style.display = 'none'; document.getElementById('2404.13274v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in the Proceedings of the 2024 ACM Symposium on User Interface Software and Technology (UIST)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.5.0; H.5.1; H.5.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.10902">arXiv:2309.10902</a> <span> [<a href="https://arxiv.org/pdf/2309.10902">pdf</a>, <a href="https://arxiv.org/format/2309.10902">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.3389/frvir.2023.1248915">10.3389/frvir.2023.1248915 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> VALID: A perceptually validated Virtual Avatar Library for Inclusion and Diversity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Do%2C+T+D">Tiffany D. Do</a>, <a href="/search/cs?searchtype=author&query=Zelenty%2C+S">Steve Zelenty</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=McMahan%2C+R+P">Ryan P. McMahan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.10902v2-abstract-short" style="display: inline;"> As consumer adoption of immersive technologies grows, virtual avatars will play a prominent role in the future of social computing. However, as people begin to interact more frequently through virtual avatars, it is important to ensure that the research community has validated tools to evaluate the effects and consequences of such technologies. We present the first iteration of a new, freely avail… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.10902v2-abstract-full').style.display = 'inline'; document.getElementById('2309.10902v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.10902v2-abstract-full" style="display: none;"> As consumer adoption of immersive technologies grows, virtual avatars will play a prominent role in the future of social computing. However, as people begin to interact more frequently through virtual avatars, it is important to ensure that the research community has validated tools to evaluate the effects and consequences of such technologies. We present the first iteration of a new, freely available 3D avatar library called the Virtual Avatar Library for Inclusion and Diversity (VALID), which includes 210 fully rigged avatars with a focus on advancing racial diversity and inclusion. We present a detailed process for creating, iterating, and validating avatars of diversity. Through a large online study (n=132) with participants from 33 countries, we provide statistically validated labels for each avatar's perceived race and gender. Through our validation study, we also advance knowledge pertaining to the perception of an avatar's race. In particular, we found that avatars of some races were more accurately identified by participants of the same race. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.10902v2-abstract-full').style.display = 'none'; document.getElementById('2309.10902v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Frontiers in Virtual Reality 4 (2023) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.12469">arXiv:2308.12469</a> <span> [<a href="https://arxiv.org/pdf/2308.12469">pdf</a>, <a href="https://arxiv.org/format/2308.12469">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tian%2C+J">Junjiao Tian</a>, <a href="/search/cs?searchtype=author&query=Aggarwal%2C+L">Lavisha Aggarwal</a>, <a href="/search/cs?searchtype=author&query=Colaco%2C+A">Andrea Colaco</a>, <a href="/search/cs?searchtype=author&query=Kira%2C+Z">Zsolt Kira</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.12469v3-abstract-short" style="display: inline;"> Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.12469v3-abstract-full').style.display = 'inline'; document.getElementById('2308.12469v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.12469v3-abstract-full" style="display: none;"> Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers. Specifically, we introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. The proposed method does not require any training or language dependency to extract quality segmentation for any images. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU. The project page is at \url{https://sites.google.com/view/diffseg/home}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.12469v3-abstract-full').style.display = 'none'; document.getElementById('2308.12469v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to CVPR2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Conference on Computer Vision and Pattern Recognition, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.12390">arXiv:2108.12390</a> <span> [<a href="https://arxiv.org/pdf/2108.12390">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3510463">10.1145/3510463 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Two-In-One: A Design Space for Mapping Unimanual Input into Bimanual Interactions in VR for Users with Limited Movement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yamagami%2C+M">Momona Yamagami</a>, <a href="/search/cs?searchtype=author&query=Junuzovic%2C+S">Sasa Junuzovic</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=Ofek%2C+E">Eyal Ofek</a>, <a href="/search/cs?searchtype=author&query=Cutrell%2C+E">Edward Cutrell</a>, <a href="/search/cs?searchtype=author&query=Porter%2C+J+R">John R. Porter</a>, <a href="/search/cs?searchtype=author&query=Wilson%2C+A+D">Andrew D. Wilson</a>, <a href="/search/cs?searchtype=author&query=Mott%2C+M+E">Martez E. Mott</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2108.12390v3-abstract-short" style="display: inline;"> Virtual Reality (VR) applications often require users to perform actions with two hands when performing tasks and interacting with objects in virtual environments. Although bimanual interactions in VR can resemble real-world interactions -- thus increasing realism and improving immersion -- they can also pose significant accessibility challenges to people with limited mobility, such as for people… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12390v3-abstract-full').style.display = 'inline'; document.getElementById('2108.12390v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.12390v3-abstract-full" style="display: none;"> Virtual Reality (VR) applications often require users to perform actions with two hands when performing tasks and interacting with objects in virtual environments. Although bimanual interactions in VR can resemble real-world interactions -- thus increasing realism and improving immersion -- they can also pose significant accessibility challenges to people with limited mobility, such as for people who have full use of only one hand. An opportunity exists to create accessible techniques that take advantage of users' abilities, but designers currently lack structured tools to consider alternative approaches. To begin filling this gap, we propose Two-in-One, a design space that facilitates the creation of accessible methods for bimanual interactions in VR from unimanual input. Our design space comprises two dimensions, bimanual interactions and computer assistance, and we provide a detailed examination of issues to consider when creating new unimanual input techniques that map to bimanual interactions in VR. We used our design space to create three interaction techniques that we subsequently implemented for a subset of bimanual interactions and received user feedback through a video elicitation study with 17 people with limited mobility. Our findings explore complex tradeoffs associated with autonomy and agency and highlight the need for additional settings and methods to make VR accessible to people with limited mobility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.12390v3-abstract-full').style.display = 'none'; document.getElementById('2108.12390v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages, 3 figures, 6 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.10829">arXiv:2108.10829</a> <span> [<a href="https://arxiv.org/pdf/2108.10829">pdf</a>, <a href="https://arxiv.org/format/2108.10829">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3472749.3474821">10.1145/3472749.3474821 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> HapticBots: Distributed Encountered-type Haptics for VR with Multiple Shape-changing Mobile Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Suzuki%2C+R">Ryo Suzuki</a>, <a href="/search/cs?searchtype=author&query=Ofek%2C+E">Eyal Ofek</a>, <a href="/search/cs?searchtype=author&query=Sinclair%2C+M">Mike Sinclair</a>, <a href="/search/cs?searchtype=author&query=Leithinger%2C+D">Daneil Leithinger</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2108.10829v1-abstract-short" style="display: inline;"> HapticBots introduces a novel encountered-type haptic approach for Virtual Reality (VR) based on multiple tabletop-size shape-changing robots. These robots move on a tabletop and change their height and orientation to haptically render various surfaces and objects on-demand. Compared to previous encountered-type haptic approaches like shape displays or robotic arms, our proposed approach has an ad… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.10829v1-abstract-full').style.display = 'inline'; document.getElementById('2108.10829v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.10829v1-abstract-full" style="display: none;"> HapticBots introduces a novel encountered-type haptic approach for Virtual Reality (VR) based on multiple tabletop-size shape-changing robots. These robots move on a tabletop and change their height and orientation to haptically render various surfaces and objects on-demand. Compared to previous encountered-type haptic approaches like shape displays or robotic arms, our proposed approach has an advantage in deployability, scalability, and generalizability -- these robots can be easily deployed due to their compact form factor. They can support multiple concurrent touch points in a large area thanks to the distributed nature of the robots. We propose and evaluate a novel set of interactions enabled by these robots which include: 1) rendering haptics for VR objects by providing just-in-time touch-points on the user's hand, 2) simulating continuous surfaces with the concurrent height and position change, and 3) enabling the user to pick up and move VR objects through graspable proxy objects. Finally, we demonstrate HapticBots with various applications, including remote collaboration, education and training, design and 3D modeling, and gaming and entertainment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.10829v1-abstract-full').style.display = 'none'; document.getElementById('2108.10829v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">UIST 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1602.01944">arXiv:1602.01944</a> <span> [<a href="https://arxiv.org/pdf/1602.01944">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Immersive Augmented Reality Training for Complex Manufacturing Scenarios </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a>, <a href="/search/cs?searchtype=author&query=Cermeron%2C+J">Julio Cermeron</a>, <a href="/search/cs?searchtype=author&query=Li%2C+K">Katie Li</a>, <a href="/search/cs?searchtype=author&query=Pizarro%2C+R">Rodrigo Pizarro</a>, <a href="/search/cs?searchtype=author&query=Thorn%2C+J">Jacob Thorn</a>, <a href="/search/cs?searchtype=author&query=Hutabarat%2C+W">Windo Hutabarat</a>, <a href="/search/cs?searchtype=author&query=Tiwari%2C+A">Ashutosh Tiwari</a>, <a href="/search/cs?searchtype=author&query=Bermell-Garcia%2C+P">Pablo Bermell-Garcia</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1602.01944v2-abstract-short" style="display: inline;"> In the complex manufacturing sector a considerable amount of resources are focused on developing new skills and training workers. In that context, increasing the effectiveness of those processes and reducing the investment required is an outstanding issue. In this paper we present an experiment that shows how modern Human Computer Interaction (HCI) metaphors such as collaborative mixed-reality can… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1602.01944v2-abstract-full').style.display = 'inline'; document.getElementById('1602.01944v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1602.01944v2-abstract-full" style="display: none;"> In the complex manufacturing sector a considerable amount of resources are focused on developing new skills and training workers. In that context, increasing the effectiveness of those processes and reducing the investment required is an outstanding issue. In this paper we present an experiment that shows how modern Human Computer Interaction (HCI) metaphors such as collaborative mixed-reality can be used to transmit procedural knowledge and could eventually replace other forms of face-to-face training. We implement a real-time Immersive Augmented Reality (IAR) setup with see-through cameras that allows for collaborative interactions that can simulate conventional forms of training. The obtained results indicate that people who took the IAR training achieved the same performance than people in the conventional face-to-face training condition. These results, their implications for future training and the use of HCI paradigms in this context are discussed in this paper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1602.01944v2-abstract-full').style.display = 'none'; document.getElementById('1602.01944v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2016; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 February, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 4 figures, Video: https://youtu.be/xCbvmGkL6Y4</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1602.00238">arXiv:1602.00238</a> <span> [<a href="https://arxiv.org/pdf/1602.00238">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/2964284.2967200">10.1145/2964284.2967200 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Assessing 3D scan quality in Virtual Reality through paired-comparisons psychophysics test </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thorn%2C+J">Jacob Thorn</a>, <a href="/search/cs?searchtype=author&query=Pizarro%2C+R">Rodrigo Pizarro</a>, <a href="/search/cs?searchtype=author&query=Spanlang%2C+B">Bernhard Spanlang</a>, <a href="/search/cs?searchtype=author&query=Bermell-Garcia%2C+P">Pablo Bermell-Garcia</a>, <a href="/search/cs?searchtype=author&query=Gonzalez-Franco%2C+M">Mar Gonzalez-Franco</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1602.00238v2-abstract-short" style="display: inline;"> Consumer 3D scanners and depth cameras are increasingly being used to generate content and avatars for Virtual Reality (VR) environments and avoid the inconveniences of hand modeling; however, it is sometimes difficult to evaluate quantitatively the mesh quality at which 3D scans should be exported, and whether the object perception might be affected by its shading. We propose using a paired-compa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1602.00238v2-abstract-full').style.display = 'inline'; document.getElementById('1602.00238v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1602.00238v2-abstract-full" style="display: none;"> Consumer 3D scanners and depth cameras are increasingly being used to generate content and avatars for Virtual Reality (VR) environments and avoid the inconveniences of hand modeling; however, it is sometimes difficult to evaluate quantitatively the mesh quality at which 3D scans should be exported, and whether the object perception might be affected by its shading. We propose using a paired-comparisons test based on psychophysics of perception to do that evaluation. As psychophysics is not subject to opinion, skill level, mental state, or economic situation it can be considered a quantitative way to measure how people perceive the mesh quality. In particular, we propose using the psychophysical measure for the comparison of four different levels of mesh quality (1K, 5K, 10K and 20K triangles). We present two studies within subjects: in one we investigate the quality perception variations of seeing an object in a regular screen monitor against an stereoscopic Head Mounted Display (HMD); while in the second experiment we aim at detecting the effects of shading into quality perception. At each iteration of the pair-test comparisons participants pick the mesh that they think had higher quality; by the end of the experiment we compile a preference matrix. The matrix evidences the correlation between real quality and assessed quality. Regarding the shading mode, we find an interaction with quality and shading when the model has high definition. Furthermore, we assess the subjective realism of the most/least preferred scans using an Immersive Augmented Reality (IAR) video-see-through setup. Results show higher levels of realism were perceived through the HMD than when using a monitor, although the quality was similarly perceived in both systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1602.00238v2-abstract-full').style.display = 'none'; document.getElementById('1602.00238v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 January, 2017; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 January, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2016. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 10 figures, video: https://youtu.be/vC3Tx07szXU</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proceedings of the 2016 ACM on Multimedia Conference (MM '16). ACM, New York, NY, USA, 147-151 </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository