CINXE.COM

Antoine Guédon

<!DOCTYPE html> <html lang="en"> <head> <title>Antoine Gu&eacutedon</title> <meta name="description" content="Antoine Gu&eacutedon"/> <meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=yes"> <meta charset="utf-8"> <!--Facebook--> <meta property="og:image" content="https://anttwo.github.io/MACARONS/example.png"> <meta property="og:image:type" content="image/jpg"> <meta property="og:image:width" content="600"> <meta property="og:image:height" content="400"> <meta property="og:type" content="website"/> <meta property="og:url" content="https://anttwo.github.io/"/> <meta property="og:title" content="MACARONS"/> <meta property="og:description" content="Personal webpage of Antoine Gu&eacutedon."/> <!--Twitter--> <meta name="twitter:card" content="summary_large_image" /> <meta name="twitter:title" content="Antoine Gu&eacutedon" /> <meta property="twitter:description" content="Personal webpage of Antoine Gu&eacutedon."/> <meta name="twitter:image" content="https://anttwo.github.io/MACARONS/example.png"> <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/4.7.0/css/font-awesome.min.css"> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> <link href="https://fonts.googleapis.com/css2?family=Roboto:ital,wght@0,100;0,300;0,400;0,500;0,700;0,900;1,100;1,300;1,400;1,500;1,700;1,900&display=swap" rel="stylesheet"> <!-- <link href="http://fonts.googleapis.com/css?family=Roboto:ital,wght@0,100;0,300;0,400;0,500;0,700;0,900;1,100;1,300;1,400;1,500;1,700;1,900&display=swap" rel="stylesheet"> --> <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.4.1/jquery.min.js"></script> <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/js/bootstrap.min.js"></script> <script src="https://kit.fontawesome.com/bacac70704.js" crossorigin="anonymous"></script> <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css"> <link rel="shortcut icon" href="resrc/icons/mathis_square_thumb_nobg.jpg"> <link href="style.css" rel="stylesheet"> <!-- Google Analytics (DO NOT copy/paste following section, setup your own analytics tag at https://analytics.google.com/analytics/web/) --> <script async src="https://www.googletagmanager.com/gtag/js?id=G-CDL4R10HKE"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'G-CDL4R10HKE'); </script> <!-- End Google Analytics --> </head> <body> <div class="container" style="padding-top:2rem;"> <div class="col-lg-6" style="text-align:left; font-size: xx-large;"> <div class="row" style="padding-left: 1.5rem;"> <h1 style="font-size: 70px;">Antoine Gu&eacutedon</h1> <h1 style="font-size: 55px;">PhD Student</h1> </div> <a href="https://imagine.enpc.fr/" style="font-weight: 400;">IMAGINE</a> / <a href="http://ligm.u-pem.fr/accueil/" style="font-weight: 400;">LIGM</a><br> <a href="https://www.ecoledesponts.fr/en">&Eacutecole des Ponts ParisTech (ENPC)</a> <p style="font-size: large;"> 6-8, Av Blaise Pascal - Cit&eacute Descartes <br> Champs-sur-Marne <br> 77455 Marne-la-Vall&eacutee cedex 2 <br> France <br> &#9993 antoine (dot) guedon (at) enpc.fr <br> </div> <div class="col-lg-6" style="text-align:center; padding-top: 2rem;"> <img src="./media/profile.jpg" alt="Profile picture" style="height: 400px;"><br> <h5 style="padding-top: 5px;"> <a href="mailto:antoine.guedon@enpc.fr" title="e-Mail" target="_blank"><i class="fa fa-envelope-square fa-3x"></i></a> <a href="https://github.com/Anttwo" title="GitHub" target="_blank"><i class="fa fa-github-square fa-3x"></i></a> <a href="https://www.linkedin.com/in/antoine-gu%C3%A9don-3a50b0156/" title="LinkedIn" target="_blank"><i class="fa fa-linkedin-square fa-3x"></i></a> <a href="https://scholar.google.com/citations?user=uvg-I8sAAAAJ&hl=fr&oi=ao" title="Google Scholar" target="_blank"><i class="ai ai-google-scholar-square ai-3x"></i></a> <a href="https://arxiv.org/search/cs?query=Gu%C3%A9don%2C+A&searchtype=author&abstracts=show&order=-announced_date_first&size=50" target="_blank"><i class="ai ai-arxiv-square ai-3x"></i></a> </h5> </div> </div> <div class="container"> <h2>Introduction</h2> <hr/> <p> I am a PhD student in the IMAGINE computer vision team of &Eacutecole des Ponts ParisTech (ENPC) and I am co-advised by <a href="https://vincentlepetit.github.io/">Vincent Lepetit (ENPC)</a> and <a href="https://imagine.enpc.fr/~monasse/">Pascal Monasse (ENPC)</a>. I am mostly interested in Image-Based Rendering (IBR) and 3D reconstruction using deep learning approaches. In particular, I worked on developing scalable approaches for simultaneously learning to reconstruct and explore 3D environments. More recently, I have been working on Novel View Synthesis and surface reconstruction in radiance fields. Before that, I studied at the Ecole polytechnique as well as the &Eacutecole normale sup&eacuterieure Paris-Saclay where I obtained the MVA MS degree. </p> </div> <div class="container"> <h2>News</h2> <hr/> <p class="label date">07-2024</p> <a href="https://anttwo.github.io/frosting/">Gaussian Frosting</a> paper has been accepted to ECCV 2024!<br> <p class="label date">04-2024</p> I was invited by <a href="https://scholar.google.com/citations?user=SXXEZhYAAAAJ&hl=en">Pr. Ko Nishino from Kyoto University</a> to work in Japan for 6 weeks. It really was a great experience!<br> <p class="label date">03-2024</p> I was invited by <a href="https://grgkopanas.github.io/">George Kopanas</a> and <a href="https://snosixtyboo.github.io/">Bernhard Kerbl</a> to give a talk about Surface Reconstruction using Gaussian Splatting during the <a href="https://3dgstutorial.github.io/index.html">3DV 2024 tutorial on Gaussian Splatting</a>.<br> <p class="label date">02-2024</p> <a href="https://anttwo.github.io/sugar/">SuGaR</a> paper has been accepted to CVPR 2024!<br> <p class="label date">03-2023</p> <a href="https://anttwo.github.io/MACARONS/">MACARONS</a> paper has been accepted to CVPR 2023!<br> <p class="label date">11-2022</p> <a href="https://arxiv.org/abs/2208.10449">SCONE</a> paper has received a Spotlight at NeurIPS 2022!<br> <p class="label date">08-2022</p> <a href="https://arxiv.org/abs/2208.10449">SCONE</a> paper has been accepted to NeurIPS 2022!<br> <p class="label date">09-2021</p> I'm starting my PhD!<br> </div> <!-- Publications --> <div class="container"> <h2>Publications</h2> <hr/> <!-- Frosting --> <div class="container" style="text-align:left; padding-top: 2rem; padding-bottom: 2rem;"> <div class="col-lg-4" style="text-align:left; padding-top: 2rem;"> <a href="https://anttwo.github.io/frosting/"> <img src="./media/frosting.png" alt="frosting" style="width: 350px;"> </a> </div> <div class="col-lg-8" style="text-align: left;"> <a href="https://anttwo.github.io/frosting/"> <h4>Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering</h4> </a> <p style="font-size: 20px;">ECCV 2024</p> <div> <a href="https://anttwo.github.io/"><b>Antoine Gu&eacutedon</b></a>, <a href="https://vincentlepetit.github.io/">Vincent Lepetit</a> </div> We propose to represent surfaces by a mesh covered with a "Frosting" layer of varying thickness and made of 3D Gaussians. This representation captures both complex volumetric effects created by fuzzy materials such as hair or grass as well as flat surfaces. Built from RGB images only, it can be rendered in real-time and animated using traditional animation tools. <br> <a class="label label-info" href="https://arxiv.org/abs/2403.14554"><i class="fa fa-file-text"></i>&nbsp;&nbsp;Paper</a> <a class="label label-info" href="https://github.com/Anttwo/Frosting"><i class="fa fa-code fa-lg" style="vertical-align: center; margin-top: 0px"></i>&nbsp;&nbsp;Code (coming soon)</a> <!-- <a class="label label-info" href="./ref.bib"><i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX</a> --> <a class="label label-info" type="button" data-toggle="collapse" data-target="#collapse4" aria-expanded="false" aria-controls="collapse4"> <i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX </a> <div class="collapse" id="collapse4"> <div class="card"> <div class="card-block"> <pre class="card-text clickselect"> @article{guedon2024frosting, title={Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering}, author={Gu{\'e}don, Antoine and Lepetit, Vincent}, journal={ECCV}, year={2024} } </div> </div> </div> </div> </div><br> <!-- SuGaR --> <div class="container" style="text-align:left; padding-top: 2rem; padding-bottom: 2rem;"> <div class="col-lg-4" style="text-align:left; padding-top: 2rem;"> <a href="https://anttwo.github.io/sugar/"> <img src="./media/sugar.png" alt="sugar" style="width: 350px;"> </a> </div> <div class="col-lg-8" style="text-align: left;"> <a href="https://anttwo.github.io/sugar/"> <h4>SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering</h4> </a> <p style="font-size: 20px;">CVPR 2024</p> <div> <a href="https://anttwo.github.io/"><b>Antoine Gu&eacutedon</b></a>, <a href="https://vincentlepetit.github.io/">Vincent Lepetit</a> </div> We introduce a method that extracts accurate and editable meshes from 3D Gaussian Splatting representations within minutes on a single GPU. This enables easy editing, sculpting, rigging, animating, or relighting of the Gaussians using traditional softwares (Blender, Unity, Unreal Engine, etc.) by manipulating the mesh instead of the Gaussians themselves. <br> <a class="label label-info" href="https://arxiv.org/abs/2311.12775"><i class="fa fa-file-text"></i>&nbsp;&nbsp;Paper</a> <a class="label label-info" href="https://github.com/Anttwo/SuGaR"><i class="fa fa-code fa-lg" style="vertical-align: center; margin-top: 0px"></i>&nbsp;&nbsp;Code</a> <!-- <a class="label label-info" href="./ref.bib"><i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX</a> --> <a class="label label-info" type="button" data-toggle="collapse" data-target="#collapse3" aria-expanded="false" aria-controls="collapse3"> <i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX </a> <div class="collapse" id="collapse3"> <div class="card"> <div class="card-block"> <pre class="card-text clickselect"> @article{guedon2023sugar, title={SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering}, author={Gu{\'e}don, Antoine and Lepetit, Vincent}, journal={CVPR}, year={2024} } </div> </div> </div> </div> </div><br> <!-- MACARONS --> <div class="container" style="text-align:left; padding-top: 2rem; padding-bottom: 2rem;"> <div class="col-lg-4" style="text-align:left; padding-top: 2rem;"> <a href="https://anttwo.github.io/MACARONS/"> <img src="./media/macarons.png" alt="macarons" style="width: 350px;"> </a> </div> <div class="col-lg-8" style="text-align: left;"> <a href="https://anttwo.github.io/MACARONS/"> <h4>MACARONS: Mapping And Coverage Anticipation with RGB ONline Self-supervision</h4> </a> <p style="font-size: 20px;">CVPR 2023</p> <div> <a href="https://anttwo.github.io/"><b>Antoine Gu&eacutedon</b></a>, <a href="https://www.tmonnier.com/">Tom Monnier</a>, <a href="https://imagine.enpc.fr/~monasse/">Pascal Monasse</a>, <a href="https://vincentlepetit.github.io/">Vincent Lepetit</a> </div> We introduce a novel method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only, in a self-supervised fashion.<br> <a class="label label-info" href="https://arxiv.org/abs/2303.03315"><i class="fa fa-file-text"></i>&nbsp;&nbsp;Paper</a> <a class="label label-info" href="https://github.com/Anttwo/MACARONS"><i class="fa fa-code fa-lg" style="vertical-align: center; margin-top: 0px"></i>&nbsp;&nbsp;Code</a> <!-- <a class="label label-info" href="./ref.bib"><i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX</a> --> <a class="label label-info" type="button" data-toggle="collapse" data-target="#collapse2" aria-expanded="false" aria-controls="collapse2"> <i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX </a> <div class="collapse" id="collapse2"> <div class="card"> <div class="card-block"> <pre class="card-text clickselect"> @inproceedings{guedon2023macarons, title={{MACARONS: Mapping And Coverage Anticipation with RGB ONline Self-supervision}}, author={Gu{\'e}don, Antoine and Monnier, Tom and Monasse, Pascal and Lepetit, Vincent}, booktitle={{CVPR}}, year={2023}, } </pre> </div> </div> </div> </div> </div><br> <!-- SCONE --> <div class="container" style="text-align:left; padding-top: 2rem; padding-bottom: 2rem;"> <div class="col-lg-4" style="text-align:left; padding-top: 2rem;"> <a href="https://arxiv.org/abs/2208.10449"> <img src="./media/scone.png" alt="scone" style="width: 350px;"> </a> </div> <div class="col-lg-8" style="text-align: left;"> <a href="https://arxiv.org/abs/2208.10449"> <h4>SCONE: Surface Coverage Optimization in uNknown Environments by Volumetric Integration</h4> </a> <p style="font-size: 20px;">NeurIPS 2022 (Spotlight)</p> <div> <a href="https://anttwo.github.io/"><b>Antoine Gu&eacutedon</b></a>, <a href="https://imagine.enpc.fr/~monasse/">Pascal Monasse</a>, <a href="https://vincentlepetit.github.io/">Vincent Lepetit</a> </div> We introduce a novel approach to solve the Next Best View problem for dense 3D reconstruction in unknown environments. Contrary to other learning-based methods, our approach scales to large 3D scenes and handles completely free camera motion at inference.<br> <a class="label label-info" href="https://arxiv.org/abs/2208.10449"><i class="fa fa-file-text"></i>&nbsp;&nbsp;Paper</a> <a class="label label-info" href="https://github.com/Anttwo/MACARONS"><i class="fa fa-code fa-lg" style="vertical-align: center; margin-top: 0px"></i>&nbsp;&nbsp;Code</a> <!-- <a class="label label-info" href="./ref.bib"><i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX</a> --> <a class="label label-info" type="button" data-toggle="collapse" data-target="#collapse1" aria-expanded="false" aria-controls="collapse1"> <i class="fa fa-commenting fa-lg" style="vertical-align:center;margin-top:0px"></i>&nbsp;&nbsp;BibTeX </a> <div class="collapse" id="collapse1"> <div class="card"> <div class="card-block"> <pre class="card-text clickselect"> @inproceedings{guedon2022scone, title={{SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration}}, author={Gu{\'e}don, Antoine and Monasse, Pascal and Lepetit, Vincent}, booktitle={{Advances in Neural Information Processing Systems}}, year={2022}, } </pre> </div> </div> </div> </div> </div> </div> <p style="text-align: center; padding-top: 2rem; font-size: 15px;"> &copy You are welcome to copy the code, please attribute the source with a link back to this page.<br> Template inspired from <a href="https://www.tmonnier.com/">Tom Monnier</a> and <a href="https://mathis.petrovich.fr/">Mathis Petrovich</a>. </p> </body>

Pages: 1 2 3 4 5 6 7 8 9 10