{"id":343085,"date":"2009-07-27T11:13:40","date_gmt":"2009-07-27T18:13:40","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=343085"},"modified":"2016-12-29T11:16:23","modified_gmt":"2016-12-29T19:16:23","slug":"kernel-nystrom-method-light-transport","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/kernel-nystrom-method-light-transport\/","title":{"rendered":"Kernel Nystr\u00f6m Method for Light Transport"},"content":{"rendered":"<p>We propose a kernel Nystr\u00f6m method for reconstructing the light transport matrix from a relatively small number of acquired images. Our work is based on the generalized Nystr\u00f6m method for low rank \u00a8 matrices. We introduce the light transport kernel and incorporate it into the Nystr\u00f6m method to exploit the nonlinear coherence of the light transport matrix. We also develop an adaptive scheme for efficiently capturing the sparsely sampled images from the scene. Our experiments indicate that the kernel Nystr\u00f6m method can achieve good reconstruction of the light transport matrix with a few hundred images and produce high quality relighting results. The kernel Nystr\u00f6m method is effective for modeling scenes with complex \u00a8 lighting effects and occlusions which have been challenging for existing techniques.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We propose a kernel Nystr\u00f6m method for reconstructing the light transport matrix from a relatively small number of acquired images. Our work is based on the generalized Nystr\u00f6m method for low rank \u00a8 matrices. We introduce the light transport kernel and incorporate it into the Nystr\u00f6m method to exploit the nonlinear coherence of the light [&hellip;]<\/p>\n","protected":false},"featured_media":343091,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13551],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-343085","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-graphics-and-multimedia","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/dxNHOOvfcNE","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/343085"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":0,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/343085\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/343091"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=343085"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=343085"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=343085"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=343085"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=343085"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=343085"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}