CINXE.COM

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <meta content="text/html; charset=UTF-8" http-equiv="content-type"> <meta name="viewport" content="width=device-width, initial-scale=1"> <title>CVPR 2018 Open Access Repository</title> <link rel="stylesheet" type="text/css" href="../../static/conf.css"> <script type="text/javascript" src="../../static/jquery.js"></script> <meta name="citation_title" content="End-to-End Recovery of Human Shape and Pose"> <meta name="citation_author" content="Kanazawa, Angjoo"> <meta name="citation_author" content="Black, Michael J."> <meta name="citation_author" content="Jacobs, David W."> <meta name="citation_author" content="Malik, Jitendra"> <meta name="citation_publication_date" content="2018"> <meta name="citation_conference_title" content="Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"> <meta name="citation_firstpage" content="7122"> <meta name="citation_lastpage" content="7131"> <meta name="citation_pdf_url" content="http://openaccess.thecvf.com/content_cvpr_2018/papers/Kanazawa_End-to-End_Recovery_of_CVPR_2018_paper.pdf"> </head> <body> <div id="header"> <div id="header_left"> <a href="http://cvpr2018.thecvf.com"><img src="../../img/cvpr2018_logo.jpg" width="175" border="0" alt="CVPR 2018"></a> <a href="http://www.cv-foundation.org/"><img src="../../img/cropped-cvf-s.jpg" width="175" height="112" border="0" alt="CVF"></a> </div> <div id="header_right"> <div id="header_title"> <a href="http://cvpr2018.thecvf.com">CVPR 2018</a> <a href="/" class="a_monochrome">open access</a> </div> <div id="help" > These CVPR 2018 papers are the Open Access versions, provided by the <a href="http://www.cv-foundation.org/">Computer Vision Foundation.</a><br> Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.</div> <div id="disclaimer" > This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.<br><br> <form action="../../CVPR2018_search.py" method="post"> <input type="text" name="query"> <input type="submit" value="Search"> </form> </div> </div> </div> <div class="clear"> </div> <div id="content"> <dl> <dd> <div id="papertitle"> End-to-End Recovery of Human Shape and Pose</div> <div id="authors"> <br><b><i>Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra Malik</i></b>; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7122-7131 </div><font size="5"> <br><b>Abstract</b> </font> <br><br><div id="abstract" > We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allows our model to be trained using in-the-wild images that only have ground truth 2D annotations. However, the reprojection loss alone is highly underconstrained. In this work we address this problem by introducing an adversary trained to tell whether human body shape and pose are real or not using a large database of 3D human meshes. We show that HMR can be trained with and without using any paired 2D-to-3D supervision. We do not rely on intermediate 2D keypoint detections and infer 3D pose and shape parameters directly from image pixels. Our model runs in real-time given a bounding box containing the person. We demonstrate our approach on various images in-the-wild and out-perform previous optimization-based methods that output 3D meshes and show competitive results on tasks such as 3D joint location estimation and part segmentation.</div> <font size="5"> <br><b>Related Material</b> </font> <br><br> [<a href="../../content_cvpr_2018/papers/Kanazawa_End-to-End_Recovery_of_CVPR_2018_paper.pdf">pdf</a>] [<a href="https://arxiv.org/abs/arXiv:1712.06584">arXiv</a>] <div class="link2">[<a class="fakelink" onclick="$(this).siblings('.bibref').slideToggle()">bibtex</a>] <div class="bibref"> @InProceedings{Kanazawa_2018_CVPR,<br> author = {Kanazawa, Angjoo and Black, Michael J. and Jacobs, David W. and Malik, Jitendra},<br> title = {End-to-End Recovery of Human Shape and Pose},<br> booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},<br> month = {June},<br> year = {2018}<br> } </div> </div> </dd> </dl> </div> </body> </html>