Jiahui Huang

<!DOCTYPE html><html lang="en-us" > <head> <meta charset="utf-8" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <meta http-equiv="X-UA-Compatible" content="IE=edge" /> <meta name="generator" content="Wowchemy 5.4.0 for Hugo" /> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin /> <link rel="preload" as="style" href="https://fonts.googleapis.com/css2?family=Montserrat:wght@400;700&family=Roboto+Mono&family=Roboto:wght@400;700&display=swap"> <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Montserrat:wght@400;700&family=Roboto+Mono&family=Roboto:wght@400;700&display=swap" media="print" onload="this.media='all'"> <meta name="author" content="Jiahui Huang" /> <meta name="description" content="Research Scientist" /> <link rel="alternate" hreflang="en-us" href="https://huangjh-pub.github.io/" /> <meta name="theme-color" content="#1565c0" /> <script src="/js/mathjax-config.js"></script> <link rel="stylesheet" href="/css/vendor-bundle.min.f1ecf783c14edc00c9320c205831ad8e.css" media="print" onload="this.media='all'"> <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/academicons@1.9.1/css/academicons.min.css" integrity="sha512-W0xM4mr6dEP9nREo7Z9z+9X70wytKvMGeDsj7ps2+xg5QPrEBXC8tAW1IFnzjR6eoJ90JmCnFzerQJTLzIEHjA==" crossorigin="anonymous" media="print" onload="this.media='all'"> <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@10.2.1/build/styles/github.min.css" crossorigin="anonymous" title="hl-light" media="print" onload="this.media='all'"> <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@10.2.1/build/styles/dracula.min.css" crossorigin="anonymous" title="hl-dark" media="print" onload="this.media='all'" disabled> <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js" integrity="" crossorigin="anonymous" async></script> <link rel="stylesheet" href="/css/wowchemy.4bcbc2330700a53eb7f390a1b72b8333.css" /> <script async src="https://www.googletagmanager.com/gtag/js?id=UA-162631457-1"></script> <script> window.dataLayer = window.dataLayer || []; function gtag() { dataLayer.push(arguments); } function trackOutboundLink(url, target) { gtag('event', 'click', { 'event_category': 'outbound', 'event_label': url, 'transport_type': 'beacon', 'event_callback': function () { if (target !== '_blank') { document.location = url; } } }); console.debug("Outbound link clicked: " + url); } function onClickCallback(event) { if ((event.target.tagName !== 'A') || (event.target.host === window.location.host)) { return; } trackOutboundLink(event.target, event.target.getAttribute('target')); } gtag('js', new Date()); gtag('config', 'UA-162631457-1', {}); gtag('set', {'cookie_flags': 'SameSite=None;Secure'}); document.addEventListener('click', onClickCallback, false); </script> <link rel="alternate" href="/index.xml" type="application/rss+xml" title="Jiahui Huang" /> <link rel="manifest" href="/manifest.webmanifest" /> <link rel="icon" type="image/png" href="/media/icon_hu6176816951213106011.png" /> <link rel="apple-touch-icon" type="image/png" href="/media/icon_hu18007185188666613945.png" /> <link rel="canonical" href="https://huangjh-pub.github.io/" /> <meta property="twitter:card" content="summary" /> <meta property="twitter:site" content="@huangjh_hjh" /> <meta property="twitter:creator" content="@huangjh_hjh" /> <meta property="og:site_name" content="Jiahui Huang" /> <meta property="og:url" content="https://huangjh-pub.github.io/" /> <meta property="og:title" content="Jiahui Huang" /> <meta property="og:description" content="Research Scientist" /><meta property="og:image" content="https://huangjh-pub.github.io/media/icon_hu7092057554204590415.png" /> <meta property="twitter:image" content="https://huangjh-pub.github.io/media/icon_hu7092057554204590415.png" /><meta property="og:locale" content="en-us" /> <meta property="og:updated_time" content="2024-12-30T23:15:32-07:00" /> <script type="application/ld+json"> { "@context": "https://schema.org", "@type": "WebSite", "potentialAction": { "@type": "SearchAction", "target": "https://huangjh-pub.github.io/?q={search_term_string}", "query-input": "required name=search_term_string" }, "url": "https://huangjh-pub.github.io/" } </script> <title>Jiahui Huang</title> </head> <body id="top" data-spy="scroll" data-offset="70" data-target="#navbar-main" class="page-wrapper " > <script src="/js/wowchemy-init.min.9e9fa4b2ccd29f9edfae161d14d2effd.js"></script> <aside class="search-modal" id="search"> <div class="container"> <section class="search-header"> <div class="row no-gutters justify-content-between mb-3"> <div class="col-6"> <h1>Search</h1> </div> <div class="col-6 col-search-close"> <a class="js-search" href="#" aria-label="Close"><i class="fas fa-times-circle text-muted" aria-hidden="true"></i></a> </div> </div> <div id="search-box"> <input name="q" id="search-query" placeholder="Search..." autocapitalize="off" autocomplete="off" autocorrect="off" spellcheck="false" type="search" class="form-control" aria-label="Search..."> </div> </section> <section class="section-search-results"> <div id="search-hits"> </div> </section> </div> </aside> <div class="page-header"> <header class="header--fixed"> <nav class="navbar navbar-expand-lg navbar-light compensate-for-scrollbar" id="navbar-main"> <div class="container-xl"> <div class="d-none d-lg-inline-flex"> <a class="navbar-brand" href="/">Jiahui Huang</a> </div> <button type="button" class="navbar-toggler" data-toggle="collapse" data-target="#navbar-content" aria-controls="navbar-content" aria-expanded="false" aria-label="Toggle navigation"> <span><i class="fas fa-bars"></i></span> </button> <div class="navbar-brand-mobile-wrapper d-inline-flex d-lg-none"> <a class="navbar-brand" href="/">Jiahui Huang</a> </div> <div class="navbar-collapse main-menu-item collapse justify-content-start" id="navbar-content"> <ul class="navbar-nav d-md-inline-flex"> <li class="nav-item"> <a class="nav-link " href="/#about" data-target="#about"><span>Home</span></a> </li> <li class="nav-item"> <a class="nav-link " href="/#publications" data-target="#publications"><span>Publications</span></a> </li> <li class="nav-item"> <a class="nav-link " href="/#projects" data-target="#projects"><span>Projects</span></a> </li> <li class="nav-item"> <a class="nav-link " href="/#contact" data-target="#contact"><span>Contact</span></a> </li> </ul> </div> <ul class="nav-icons navbar-nav flex-row ml-auto d-flex pl-md-2"> </ul> </div> </nav> </header> </div> <div class="page-body"> <span class="js-widget-page d-none"></span> <section id="about" class="home-section wg-about " > <div class="home-section-bg " > </div> <div class="container"> <div class="row"> <div class="col-12 col-lg-4"> <div id="profile"> <img class="avatar avatar-circle" width="270" height="270" src="/authors/jiahui-huang/avatar_hu15072945850406332842.jpg" alt="Jiahui Huang"> <div class="portrait-title"> <h2>Jiahui Huang</h2> <h3>Research Scientist</h3> </div> <ul class="network-icon" aria-hidden="true"> <li> <a href="/#contact" aria-label="envelope"> <i class="fas fa-envelope big-icon"></i> </a> </li> <li> <a href="https://twitter.com/huangjh_hjh" target="_blank" rel="noopener" aria-label="twitter"> <i class="fab fa-twitter big-icon"></i> </a> </li> <li> <a href="https://scholar.google.com/citations?user=3Cuki_wAAAAJ&hl=en" target="_blank" rel="noopener" aria-label="google-scholar"> <i class="ai ai-google-scholar big-icon"></i> </a> </li> <li> <a href="https://github.com/huangjh-pub" target="_blank" rel="noopener" aria-label="github"> <i class="fab fa-github big-icon"></i> </a> </li> </ul> </div> </div> <div class="col-12 col-lg-8"> <h1>Nice to meet you.</h1> <div class="article-style"> <p>I am currently a research scientist at <a href="https://research.nvidia.com/labs/toronto-ai/" target="_blank" rel="noopener">NVIDIA Toronto AI Lab</a> led by <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a>. I received my Ph.D. in 2023 from the <a href="https://cg.cs.tsinghua.edu.cn" target="_blank" rel="noopener">Graphics and Geometric Computing Group</a> at Tsinghua University, China, advised by <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a>. I was also a visiting researcher in the <a href="https://geometry.stanford.edu/index.html" target="_blank" rel="noopener">Geometric Computing group</a> at Stanford University, led by <a href="https://geometry.stanford.edu/member/guibas/index.html" target="_blank" rel="noopener">Leonidas Guibas</a>. My primary research interest lies in the joint field of 3D computer vision and graphics, including neural reconstruction, dynamic scene perception, and SLAM.</p> <p>⛵️ We are actively looking for interns to work with at NVIDIA Research. Please reach out to me if you are interested in the position.</p> <blockquote> <p> <i class="far fa-clock pr-6 fa-fw"></i> This page was last updated in Jan 2025.</p> </blockquote> </div> <div class="row"> <div class="col-md-5"> <div class="section-subheading">Interests</div> <ul class="ul-interests mb-0"> <li>3D Computer Vision</li> <li>Computer Graphics</li> <li>Machine Learning</li> </ul> </div> <div class="col-md-7"> <div class="section-subheading">Education</div> <ul class="ul-edu fa-ul mb-0"> <li> <i class="fa-li fas fa-graduation-cap"></i> <div class="description"> <p class="course">PhD in Computer Science, 2018 - 2023</p> <p class="institution">Tsinghua University</p> </div> </li> <li> <i class="fa-li fas fa-graduation-cap"></i> <div class="description"> <p class="course">BEng in Computer Science, 2014 - 2018</p> <p class="institution">Tsinghua University</p> </div> </li> </ul> </div> </div> </div> </div> </div> </section> <section id="publications" class="home-section wg-pages " > <div class="home-section-bg " > </div> <div class="container"> <div class="row "> <div class="section-heading col-12 col-lg-4 mb-3 mb-lg-0 d-flex flex-column align-items-center align-items-lg-start"> <h1 class="mb-0">Selected Publications</h1> <p class="mt-1">See <a href="publication">Full List</a></p> </div> <div class="col-12 col-lg-8">   <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes </div> <div class="article-style"> ArXiv 2025 </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://jiawei-yang.github.io/" target="_blank" rel="noopener">Jiawei Yang</a></span>, <span class="author-highlighted"> Jiahui Huang</span>, <span > Yuxiao Chen</span>, <span > Yan Wang</span>, <span > Boyi Li</span>, <span > Yurong You</span>, <span > Maximilian Igl</span>, <span > Apoorva Sharma</span>, <span > Peter Karkus</span>, <span > Danfei Xu</span>, <span > <a href="https://www.borisivanovic.com/" target="_blank" rel="noopener">Boris Ivanovic</a></span>, <span > <a href="https://yuewang.xyz/" target="_blank" rel="noopener">Yue Wang</a></span>, <span > Marco Pavone</span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2501.00602" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://jiawei-yang.github.io/STORM/" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/storm/" > <img src="/publication/storm/featured.gif" height="247" width="480" alt="STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models </div> <div class="article-style"> ArXiv 2024 </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://yifanlu0227.github.io/" target="_blank" rel="noopener">Yifan Lu</a></span>, <span > <a href="https://xuanchiren.com/" target="_blank" rel="noopener">Xuanchi Ren</a></span>, <span > <a href="https://jiawei-yang.github.io/" target="_blank" rel="noopener">Jiawei Yang</a></span>, <span > <a href="https://www.cs.toronto.edu/~shenti11/" target="_blank" rel="noopener">Tianchang Shen</a></span>, <span > <a href="https://zhangjiewu.github.io/" target="_blank" rel="noopener">Jay Zhangjie Wu</a></span>, <span > <a href="https://www.cs.toronto.edu/~jungao/" target="_blank" rel="noopener">Jun Gao</a></span>, <span > <a href="https://yuewang.xyz/" target="_blank" rel="noopener">Yue Wang</a></span>, <span > Siheng Chen</span>, <span > Mike Chen</span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span class="author-highlighted"> Jiahui Huang</span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2412.03934" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://research.nvidia.com/labs/toronto-ai/infinicube/" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/infinicube/" > <img src="/publication/infinicube/featured.gif" height="333" width="500" alt="InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos </div> <div class="article-style"> ArXiv 2024 </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://hanxuel.github.io/" target="_blank" rel="noopener">Hanxue Liang</a></span>, <span > <a href="https://jiawei-ren.github.io/" target="_blank" rel="noopener">Jiawei Ren</a></span>, <span > Ashkan Mirzaei</span>, <span > Antonio Torralba</span>, <span > Ziwei Liu</span>, <span > Igor Gilitschenski</span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span > Cengiz Oztireli</span>, <span > <a href="https://www.cs.toronto.edu/~linghuan/" target="_blank" rel="noopener">Huan Ling</a></span>, <span > <a href="https://zgojcic.github.io/" target="_blank" rel="noopener">Zan Gojcic</a></span>, <span class="author-highlighted"> Jiahui Huang</span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2412.03526" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://research.nvidia.com/labs/toronto-ai/bullet-timer/" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/btimer/" > <img src="/publication/btimer/featured.gif" height="338" width="600" alt="Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> SCube: Instant Large-Scale Scene Reconstruction using VoxSplats </div> <div class="article-style"> NeurIPS 2024 </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://xuanchiren.com/" target="_blank" rel="noopener">Xuanchi Ren</a></span>, <span > <a href="https://yifanlu0227.github.io/" target="_blank" rel="noopener">Yifan Lu</a></span>, <span > <a href="https://hanxuel.github.io/" target="_blank" rel="noopener">Hanxue Liang</a></span>, <span > <a href="https://zhangjiewu.github.io/" target="_blank" rel="noopener">Jay Zhangjie Wu</a></span>, <span > <a href="https://www.cs.toronto.edu/~linghuan/" target="_blank" rel="noopener">Huan Ling</a></span>, <span > Mike Chen</span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span > <a href="https://www.fwilliams.info/" target="_blank" rel="noopener">Francis Williams</a></span>, <span class="author-highlighted"> Jiahui Huang</span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2410.20030" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/nv-tlabs/scube" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://research.nvidia.com/labs/toronto-ai/scube/" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/scube/" > <img src="/publication/scube/featured.gif" height="320" width="480" alt="SCube: Instant Large-Scale Scene Reconstruction using VoxSplats" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> OmniRe: Omni Urban Scene Reconstruction </div> <div class="article-style"> ArXiv 2024 </div> <div class="stream-meta article-metadata"> <div> <span > Ziyu Chen</span>, <span > <a href="https://jiawei-yang.github.io/" target="_blank" rel="noopener">Jiawei Yang</a></span>, <span class="author-highlighted"> Jiahui Huang</span>, <span > Riccardo De Lutio</span>, <span > Janick Martinez Esturo</span>, <span > <a href="https://www.borisivanovic.com/" target="_blank" rel="noopener">Boris Ivanovic</a></span>, <span > <a href="https://orlitany.github.io/" target="_blank" rel="noopener">Or Litany</a></span>, <span > <a href="https://zgojcic.github.io/" target="_blank" rel="noopener">Zan Gojcic</a></span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span > Marco Pavone</span>, <span > Li Song</span>, <span > <a href="https://yuewang.xyz/" target="_blank" rel="noopener">Yue Wang</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2408.16760" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/ziyc/drivestudio" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://ziyc.github.io/omnire/" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/omnire/" > <img src="/publication/omnire/featured.gif" height="338" width="600" alt="OmniRe: Omni Urban Scene Reconstruction" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence </div> <div class="article-style"> SIGGRAPH 2024 </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://www.fwilliams.info/" target="_blank" rel="noopener">Francis Williams</a></span>, <span class="author-highlighted"> Jiahui Huang</span>, <span > Jonathan Swartz</span>, <span > Gergely Klár</span>, <span > Vijay Thakkar</span>, <span > Matthew Cong</span>, <span > <a href="https://xuanchiren.com/" target="_blank" rel="noopener">Xuanchi Ren</a></span>, <span > Ruilong Li</span>, <span > Clement Fuji-Tsang</span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span > Eftychios Sifakis</span>, <span > Ken Museth</span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://research.nvidia.com/labs/prl/williams2024fVDB/fVDB.pdf" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://developer.nvidia.com/fvdb" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=6JCp0hXb3S4" target="_blank" rel="noopener"> Video </a> </div> </div> <div class="ml-3"> <a href="/publication/fvdb/" > <img src="/publication/fvdb/featured_hu4740247905180417205.webp" height="321" width="550" alt="fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies </div> <div class="article-style"> Computer Vision and Pattern Recognition (CVPR) 2024 - <strong>Highlight</strong> </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://xuanchiren.com/" target="_blank" rel="noopener">Xuanchi Ren</a></span>, <span class="author-highlighted"> Jiahui Huang</span>, <span > Xiaohui Zeng</span>, <span > Ken Museth</span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span > <a href="https://www.fwilliams.info/" target="_blank" rel="noopener">Francis Williams</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2312.03806" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://research.nvidia.com/labs/toronto-ai/xcube/" target="_blank" rel="noopener"> Project </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=GX0lzwy8nUI" target="_blank" rel="noopener"> Video </a> </div> </div> <div class="ml-3"> <a href="/publication/xcube/" > <img src="/publication/xcube/featured_hu7916329372638087273.webp" height="367" width="550" alt="XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion </div> <div class="article-style"> International Conference on Computer Vision (ICCV) 2023 </div> <div class="stream-meta article-metadata"> <div> <span > <a href="https://georgenakayama.github.io/" target="_blank" rel="noopener">Kiyohiro Nakayama</a></span>, <span > <a href="https://mikacuy.github.io/" target="_blank" rel="noopener">Mikaela Angelina Uy</a></span>, <span class="author-highlighted"> Jiahui Huang</span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span>, <span > <a href="http://www.sfu.ca/~keli/" target="_blank" rel="noopener">Ke Li</a></span>, <span > <a href="https://geometry.stanford.edu/member/guibas/" target="_blank" rel="noopener">Leonidas J. Guibas</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2305.01921" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://difffacto.github.io/" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/diffacto/" > <img src="/publication/diffacto/featured_hu586507740841966265.webp" height="495" width="550" alt="DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> Neural Kernel Surface Reconstruction </div> <div class="article-style"> Computer Vision and Pattern Recognition (CVPR) 2023 - <strong>Highlight</strong> </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > <a href="https://zgojcic.github.io/" target="_blank" rel="noopener">Zan Gojcic</a></span>, <span > <a href="https://matanatz.github.io/" target="_blank" rel="noopener">Matan Atzmon</a></span>, <span > <a href="https://orlitany.github.io/" target="_blank" rel="noopener">Or Litany</a></span>, <span > <a href="https://www.cs.utoronto.ca/~fidler/" target="_blank" rel="noopener">Sanja Fidler</a></span>, <span > <a href="https://www.fwilliams.info/" target="_blank" rel="noopener">Francis Williams</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/pdf/2305.19590.pdf" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/nv-tlabs/nksr" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="/publication/nksr" target="_blank" rel="noopener"> Project </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=J1V5F2z-dWY" target="_blank" rel="noopener"> Video </a> </div> </div> <div class="ml-3"> <a href="/publication/nksr/" > <img src="/publication/nksr/featured.gif" height="352" width="640" alt="Neural Kernel Surface Reconstruction" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> A Neural Galerkin Solver for Accurate Surface Reconstruction </div> <div class="article-style"> SIGGRAPH Asia 2022 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > Hao-Xiang Chen</span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://dl.acm.org/doi/abs/10.1145/3550454.3555457" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/huangjh-pub/neural-galerkin" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=QT5k0ZxDFfo" target="_blank" rel="noopener"> Video </a> </div> </div> <div class="ml-3"> <a href="/publication/neuralgalerkin/" > <img src="/publication/neuralgalerkin/featured_hu9845969383999976422.webp" height="323" width="550" alt="A Neural Galerkin Solver for Accurate Surface Reconstruction" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization </div> <div class="article-style"> T-PAMI 2022 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > <a href="https://scholar.google.com/citations?user=_Bxd5ggAAAAJ&hl=en" target="_blank" rel="noopener">Tolga Birdal</a></span>, <span > <a href="https://zgojcic.github.io/" target="_blank" rel="noopener">Zan Gojcic</a></span>, <span > <a href="https://geometry.stanford.edu/member/guibas/" target="_blank" rel="noopener">Leonidas J. Guibas</a></span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="/synorim-arxiv.pdf" target="_blank" rel="noopener"> PDF </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/huangjh-pub/synorim" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="/publication/synorim" target="_blank" rel="noopener"> Project </a> </div> </div> <div class="ml-3"> <a href="/publication/synorim/" > <img src="/publication/synorim/featured_hu6008967279862075482.webp" height="404" width="550" alt="Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization </div> <div class="article-style"> Computer Vision and Pattern Recognition (CVPR) 2021 - <strong>Oral</strong> </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > He Wang</span>, <span > <a href="https://scholar.google.com/citations?user=_Bxd5ggAAAAJ&hl=en" target="_blank" rel="noopener">Tolga Birdal</a></span>, <span > Minhyuk Sung</span>, <span > Federica Arrigoni</span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span>, <span > <a href="https://geometry.stanford.edu/member/guibas/" target="_blank" rel="noopener">Leonidas J. Guibas</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2101.06605" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/publication/multibodysync/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/huangjh-pub/multibody-sync" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://github.com/huangjh-pub/multibody-sync" target="_blank" rel="noopener"> Dataset </a> </div> </div> <div class="ml-3"> <a href="/publication/multibodysync/" > <img src="/publication/multibodysync/featured_hu10019484675959133340.webp" height="348" width="550" alt="MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors </div> <div class="article-style"> Computer Vision and Pattern Recognition (CVPR) 2021 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > <a href="https://shishenghuang.github.io/index/" target="_blank" rel="noopener">Shi-Sheng Huang</a></span>, <span > Haoxuan Song</span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="http://arxiv.org/abs/2012.05551" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/publication/difusion/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.github.com/huangjh-pub/di-fusion" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=yxkIQFXQ6rw" target="_blank" rel="noopener"> Video </a> </div> </div> <div class="ml-3"> <a href="/publication/difusion/" > <img src="/publication/difusion/featured_hu7583552530714051995.webp" height="392" width="550" alt="DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> WallNet: Reconstructing General Room Layouts from RGB Images </div> <div class="article-style"> Graphical Models 2020 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > Zheng-Fei Kuang</span>, <span > Fang-Lue Zhang</span>, <span > Tai-Jiang Mu</span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.sciencedirect.com/science/article/pii/S1524070320300205" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/publication/wallnet/cite.bib"> Cite </a> </div> </div> <div class="ml-3"> <a href="/publication/wallnet/" > <img src="/publication/wallnet/featured_hu18118852651906860955.webp" height="319" width="550" alt="WallNet: Reconstructing General Room Layouts from RGB Images" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings </div> <div class="article-style"> Computer Vision and Pattern Recognition (CVPR) 2020 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > Sheng Yang</span>, <span > Tai-Jiang Mu</span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://arxiv.org/abs/2003.12980" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/publication/clustervo/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://drive.google.com/file/d/1zQr11Ne_52HTXcIHRH5rsbfuhi4B8HJZ/view?usp=sharing" target="_blank" rel="noopener"> Code </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="/clustervo-slides.pdf" target="_blank" rel="noopener"> Slides </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://www.youtube.com/watch?v=paK-WCQpX-Y" target="_blank" rel="noopener"> Video </a> </div> </div> <div class="ml-3"> <a href="/publication/clustervo/" > <img src="/publication/clustervo/featured_hu9846679181619679132.webp" height="496" width="550" alt="ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation </div> <div class="article-style"> International Conference on Computer Vision (ICCV) 2019 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > Sheng Yang</span>, <span > Zishuo Zhao</span>, <span > Yu-Kun Lai</span>, <span > <a href="https://cg.cs.tsinghua.edu.cn/shimin.htm" target="_blank" rel="noopener">Shi-Min Hu</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="http://openaccess.thecvf.com/content_ICCV_2019/papers/Huang_ClusterSLAM_A_SLAM_Backend_for_Simultaneous_Rigid_Body_Clustering_and_ICCV_2019_paper.pdf" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/publication/clusterslam/cite.bib"> Cite </a> <a class="btn btn-outline-primary btn-page-header btn-sm" href="/page/clusterslam-dataset/" target="_blank" rel="noopener"> Dataset </a> </div> </div> <div class="ml-3"> <a href="/publication/clusterslam/" > <img src="/publication/clusterslam/featured_hu7130361884708606970.webp" height="320" width="550" alt="ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation" loading="lazy"> </a> </div> </div> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> DeepPrimitive: Image decomposition by layered primitive detection </div> <div class="article-style"> Computational Visual Media (CVM) 2018 </div> <div class="stream-meta article-metadata"> <div> <span class="author-highlighted"> Jiahui Huang</span>, <span > <a href="https://www.cs.toronto.edu/~jungao/" target="_blank" rel="noopener">Jun Gao</a></span>, <span > Vignesh Ganapathi-Subramanian</span>, <span > Hao Su</span>, <span > Yin Liu</span>, <span > Chengcheng Tang</span>, <span > <a href="https://geometry.stanford.edu/member/guibas/" target="_blank" rel="noopener">Leonidas J. Guibas</a></span> </div> </div> <div class="btn-links"> <a class="btn btn-outline-primary btn-page-header btn-sm" href="https://link.springer.com/article/10.1007/s41095-018-0128-6" target="_blank" rel="noopener"> PDF </a> <a href="#" class="btn btn-outline-primary btn-page-header btn-sm js-cite-modal" data-filename="/publication/deepprimitive/cite.bib"> Cite </a> </div> </div> <div class="ml-3"> <a href="/publication/deepprimitive/" > <img src="/publication/deepprimitive/featured_hu15760638383232042689.webp" height="259" width="550" alt="DeepPrimitive: Image decomposition by layered primitive detection" loading="lazy"> </a> </div> </div> </div> </div> </div> </section> <section id="projects" class="home-section wg-portfolio " > <div class="home-section-bg " > </div> <div class="container"> <div class="row "> <div class="section-heading col-12 col-lg-4 mb-3 mb-lg-0 d-flex flex-column align-items-center align-items-lg-start"> <h1 class="mb-0">Projects</h1> </div> <div class="col-12 col-lg-8"> <div class=" row js-layout-row "> <div class="col-12 isotope-item "> <div class="media stream-item view-compact"> <div class="media-body"> <div class="section-subheading article-title mb-0 mt-0"> <a href="project/3sweep/" target="_blank" rel="noopener">3-Sweep: Extracting Editable Objects from a Single Photo</a> </div> <a href="project/3sweep/" target="_blank" rel="noopener" class="summary-link"> <div class="article-style"> 3-Sweep is a creative method for 3D modeling from a single image, which is proposed in a SIGGRAPH ASIA 2013 paper by Tsinghua University, Tel Aviv University and The Interdisciplinary Center. According to many readers’ requests, I re-implemented and released this software. </div> </a> <div class="stream-meta article-metadata"> </div> </div> <div class="ml-3"> <a href="project/3sweep/" target="_blank" rel="noopener"> <img src="/project/3sweep-dummy/featured_hu6227738526307653871.webp" height="613" width="550" alt="3-Sweep: Extracting Editable Objects from a Single Photo" loading="lazy"> </a> </div> </div> </div> </div> </div> </div> </div> </section> <section id="contact" class="home-section wg-contact " > <div class="home-section-bg " > </div> <div class="container"> <div class="row "> <div class="section-heading col-12 col-lg-4 mb-3 mb-lg-0 d-flex flex-column align-items-center align-items-lg-start"> <h1 class="mb-0">Contact</h1> </div> <div class="col-12 col-lg-8"> <ul class="fa-ul"> <li> <i class="fa-li fas fa-envelope fa-2x" aria-hidden="true"></i> <span id="person-email"><a href="mailto:huangjh.connect@outlook.com">huangjh.connect@outlook.com</a></span> </li> <li> <i class="fa-li fas fa-map-marker fa-2x" aria-hidden="true"></i> <span id="person-address">2788 San Tomas Expy, Santa Clara, CA 90501</span> </li> </ul> </div> </div> </div> </section> </div> <div class="page-footer"> <div class="container"> <footer class="site-footer"> <p class="powered-by copyright-license-text"> © 2020-2025 Jiahui Huang All Rights Reserved. </p> <p class="powered-by"> Published with <a href="https://wowchemy.com/?utm_campaign=poweredby" target="_blank" rel="noopener">Wowchemy</a> — the free, <a href="https://github.com/wowchemy/wowchemy-hugo-themes" target="_blank" rel="noopener">open source</a> website builder that empowers creators. </p> </footer> </div> </div> <script src="/js/vendor-bundle.min.8e09daa601459f1768414cc0569ad616.js"></script> <script src="https://cdn.jsdelivr.net/gh/desandro/imagesloaded@v4.1.4/imagesloaded.pkgd.min.js" integrity="sha512-S5PZ9GxJZO16tT9r3WJp/Safn31eu8uWrzglMahDT4dsmgqWonRY9grk3j+3tfuPr9WJNsfooOR7Gi7HL5W2jw==" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/gh/metafizzy/isotope@v3.0.6/dist/isotope.pkgd.min.js" integrity="sha512-Zq2BOxyhvnRFXu0+WE6ojpZLOU2jdnqbrM1hmVdGzyeCa1DgM3X5Q4A/Is9xA1IkbUeDd7755dNNI/PzSf2Pew==" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@10.2.1/build/highlight.min.js" integrity="sha512-Ypjm0o7jOxAd4hpdoppSEN0TQOC19UtPAqD+4s5AlXmUvbmmS/YMxYqAqarQYyxTnB6/rqip9qcxlNB/3U9Wdg==" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@10.2.1/build/languages/r.min.js" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@10.2.1/build/languages/latex.min.js" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@10.2.1/build/languages/bibtex.min.js" crossorigin="anonymous"></script> <script id="search-hit-fuse-template" type="text/x-template"> <div class="search-hit" id="summary-{{key}}"> <div class="search-hit-content"> <div class="search-hit-name"> <a href="{{relpermalink}}">{{title}}</a> <div class="article-metadata search-hit-type">{{type}}</div> <p class="search-hit-description">{{snippet}}</p> </div> </div> </div> </script> <script src="https://cdn.jsdelivr.net/gh/krisk/Fuse@v3.2.1/dist/fuse.min.js" integrity="sha512-o38bmzBGX+hD3JHWUFCDA09btWaqrNmoJ3RXLlrysA7PP01Kgs4UlE4MhelE1v5dJR3+cxlR4qQlotsW7jKsnw==" crossorigin="anonymous"></script> <script src="https://cdn.jsdelivr.net/gh/julmot/mark.js@8.11.1/dist/jquery.mark.min.js" integrity="sha512-mhbv5DqBMgrWL+32MmsDOt/OAvqr/cHimk6B8y/bx/xS88MVkYGPiVv2ixKVrkywF2qHplNRUvFsAHUdxZ3Krg==" crossorigin="anonymous"></script> <script id="page-data" type="application/json">{"use_headroom":false}</script> <script src="/en/js/wowchemy.min.5745db4f02c04a35c01d84b183b3a15c.js"></script> <div id="modal" class="modal fade" role="dialog"> <div class="modal-dialog"> <div class="modal-content"> <div class="modal-header"> <h5 class="modal-title">Cite</h5> <button type="button" class="close" data-dismiss="modal" aria-label="Close"> <span aria-hidden="true">×</span> </button> </div> <div class="modal-body"> <pre><code class="tex hljs"></code></pre> </div> <div class="modal-footer"> <a class="btn btn-outline-primary my-1 js-copy-cite" href="#" target="_blank"> <i class="fas fa-copy"></i> Copy </a> <a class="btn btn-outline-primary my-1 js-download-cite" href="#" target="_blank"> <i class="fas fa-download"></i> Download </a> <div id="modal-error"></div> </div> </div> </div> </div> <script src="/js/wowchemy-publication.6067f855b31c86c97091c0d8b69206f5.js" type="module"></script> </body> </html>

CINXE.COM

Jiahui Huang