{"id":240,"date":"2020-06-16T17:17:43","date_gmt":"2020-06-16T17:17:43","guid":{"rendered":"https:\/\/realitylab.uw.edu\/staging\/?p=240"},"modified":"2020-06-17T21:19:32","modified_gmt":"2020-06-17T21:19:32","slug":"uw-reality-lab-at-cvpr20","status":"publish","type":"post","link":"https:\/\/realitylab.uw.edu\/staging\/?p=240","title":{"rendered":"UW Reality Lab at CVPR&#8217;20"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Two of the UW Reality Lab Directors each gave a keynote address at CVPR&#8217;20, and several of our researchers have papers, posters, and presentations there:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Prof. Ira Kemelmacher-Shlizerman<\/strong> (Director of the UW Reality Lab) gave a keynote at the <a href=\"https:\/\/vuhcs.github.io\/\">Human-Centric Image\/Video Synthesis Workshop<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Prof. Steve Seitz<\/strong> (Co-Director of the UW Reality Lab) gave a keynote at the <a href=\"https:\/\/mixedreality.cs.cornell.edu\/workshop\/2020\/program\">Fourth Workshop on Computer Vision for AR\/VR<\/a><\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p class=\"wp-block-paragraph\"><strong><a href=\"https:\/\/drive.google.com\/file\/d\/1MGIC9OsMq-Timi8ZGoRXVSTS3ALs3IoR\/view\">Slow Glass: Visualizing History in 3D<\/a><\/strong><br><em>(Xuan Luo, Yanmeng Kong, Jason Lawrence, Ricardo Martin Brualla, Steven M. Seitz)<\/em><\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Slow Glass: Visualizing History in 3D (CV4ARVR 2020)\" width=\"800\" height=\"450\" src=\"https:\/\/www.youtube.com\/embed\/GQiqaxYmTeo?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>Wouldn&#8217;t it be fascinating to be in the same room as Abraham Lincoln, visit Thomas Edison in his laboratory, or step onto the streets of New York a hundred years ago?  We explore this thought experiment, by tracing ideas from science fiction through newly available data sources that may facilitate this goal.<\/p><\/blockquote>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p style=\"color:#053bb0;font-size:18px\" class=\"has-text-color wp-block-paragraph\"><strong><a href=\"https:\/\/grail.cs.washington.edu\/projects\/background-matting\/\">Background Matting: The World is Your Green Screen<\/a><\/strong><br><em>(Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman)<\/em><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This project was used by Microsoft\u2019s Build Conference, and <a href=\"https:\/\/youtu.be\/6ml8kr1M1Pw?t=509\">Microsoft CEO Satya Nadella<\/a> talked about it in this Fireside Chat:<\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Fireside Chat with Satya Nadella\" width=\"800\" height=\"450\" src=\"https:\/\/www.youtube.com\/embed\/6ml8kr1M1Pw?start=509&#038;feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>\u201cThe next area, Harry, that we\u2019re  all so excited about in this world of remote everything, is Background  Matting &#8230;we recently had the Build Developer Conference and we were able to take presenters who just recorded themselves at home, and then we were able in fact to superimpose them in  a virtual stage without needing that Green Screen. &#8230;Again, breakthroughs in computer vision that, in fact, we worked with  the University of Washington on. So let\u2019s roll the video.\u201d <\/p><cite>\u2013 Satya Nadella<\/cite><\/blockquote>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p style=\"color:#053bb0;font-size:18px\" class=\"has-text-color wp-block-paragraph\"><strong><a href=\"https:\/\/arxiv.org\/abs\/2001.04642\">Seeing the World in a Bag of Chips<\/a><\/strong><br><em>(Jeong Joon Park, Aleksander Holynski, Steve Seitz)<\/em><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"833\" height=\"265\" src=\"https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/chips.jpg\" alt=\"\" class=\"wp-image-264\" srcset=\"https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/chips.jpg 833w, https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/chips-300x95.jpg 300w, https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/chips-768x244.jpg 768w\" sizes=\"auto, (max-width: 833px) 100vw, 833px\" \/><\/figure>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>We address the dual problems of novel view synthesis and environment reconstruction from hand-held RGBD sensors. Our contributions include 1) modeling highly specular objects, 2) modeling inter-reflections and Fresnel effects, and 3) enabling surface light field reconstruction with the same input needed to reconstruct shape alone. In cases where scene surface has a strong mirror-like material component, we generate highly detailed environment images, revealing room composition, objects, people, buildings, and trees visible through windows. Our approach yields state of the art view synthesis techniques, operates on low dynamic range imagery, and is robust to geometric and calibration errors.      <\/p><\/blockquote>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p style=\"color:#053bb0;font-size:18px\" class=\"has-text-color wp-block-paragraph\"><strong><a href=\"https:\/\/izadinia.github.io\/LICP\/\">Scene Recomposition by Learning-Based ICP <\/a><\/strong><br><em>(Hamid Izadinia, Steve Seitz<\/em>)<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"391\" src=\"https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/licp_teaser-1024x391.jpg\" alt=\"\" class=\"wp-image-281\" srcset=\"https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/licp_teaser-1024x391.jpg 1024w, https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/licp_teaser-300x114.jpg 300w, https:\/\/realitylab.uw.edu\/staging\/wp-content\/uploads\/2020\/06\/licp_teaser-768x293.jpg 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>By moving a depth sensor around a room, we compute a 3D CAD model of the  environment, capturing the room shape and contents such as chairs,  desks, sofas, and tables. Rather than reconstructing geometry, we match,  place, and align each object in the scene to thousands of CAD models of  objects. In addition to the fully automatic system, the key technical  contribution is a novel approach for aligning CAD models to 3D scans,  based on deep reinforcement learning. This approach, which we call  Learning-based ICP, outperforms prior ICP methods in the literature, by  learning the best points to match and conditioning on object viewpoint.  LICP learns to align using only synthetic data and does not require  ground truth annotation of object pose or keypoint pair matching in real  scene scans. While LICP is trained on synthetic data and without 3D  real scene annotations, it outperforms both learned local deep feature  matching and geometric based alignment methods in real scenes. The  proposed method is evaluated on real scenes datasets of SceneNN and  ScanNet as well as synthetic scenes of SUNCG. High quality results are  demonstrated on a range of real world scenes, with robustness to  clutter, viewpoint, and occlusion. <\/p><\/blockquote>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p style=\"color:#053bb0;font-size:18px\" class=\"has-text-color wp-block-paragraph\"><strong><a href=\"https:\/\/keunhong.com\/publications\/latentfusion\/\">Latent Fusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation<\/a><\/strong><br><em>(Keunhong Park, Arsalan Mousavian, Yu Xiang, Dieter Fox)<\/em><\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"LatentFusion: E2E Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation\" width=\"800\" height=\"450\" src=\"https:\/\/www.youtube.com\/embed\/tlzcq1KYXd8?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Two of the UW Reality Lab Directors each gave a keynote address at CVPR&#8217;20, and several of our researchers have papers, posters, and presentations there: Prof. Ira Kemelmacher-Shlizerman (Director of&#8230; <a class=\"read-more-link\" href=\"https:\/\/realitylab.uw.edu\/staging\/?p=240\">Read more &raquo;<\/a><\/p>\n","protected":false},"author":8,"featured_media":267,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[1],"tags":[],"class_list":["post-240","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized","gt-excerpt","gt-excerpt-thumbnail-square"],"_links":{"self":[{"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/posts\/240","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=240"}],"version-history":[{"count":37,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/posts\/240\/revisions"}],"predecessor-version":[{"id":292,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/posts\/240\/revisions\/292"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=\/wp\/v2\/media\/267"}],"wp:attachment":[{"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=240"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=240"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/realitylab.uw.edu\/staging\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=240"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}