{"id":182323,"date":"2008-09-15T00:00:00","date_gmt":"2009-10-31T09:33:39","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/candidate-talk-matching-and-3d-reconstruction-in-urban-environments\/"},"modified":"2016-09-09T09:44:00","modified_gmt":"2016-09-09T16:44:00","slug":"candidate-talk-matching-and-3d-reconstruction-in-urban-environments","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/candidate-talk-matching-and-3d-reconstruction-in-urban-environments\/","title":{"rendered":"Candidate Talk: Matching and 3D reconstruction in urban environments"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Indoor and outdoor urban environments possess many regularities which can be efficiently exploited and used for general image parsing tasks, matching, or 3D dense reconstruction from multiple widely separated views. These environments exhibit often shadows, lack textured areas, or contain repetitive textures which multiply the ambiguities in standard computer vision pipelines. During my talk I will consider those specific environments and show the way we tackle the aforementioned problems.<br \/>\nFirst, I will present an approach for detecting rectilinear structures and demonstrate their use for wide baseline stereo matching, planar 3D reconstruction, and computation of geometric context. Second, I will focus on a dense stereo method utilizing properties of piecewise planarity and restricted number of plane orientations to suppress 3D reconstruction and matching ambiguities. We show how the utilization of the scene priors yields more accurate and visually plausible results in many urban scenes compared to the standard general methods.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Indoor and outdoor urban environments possess many regularities which can be efficiently exploited and used for general image parsing tasks, matching, or 3D dense reconstruction from multiple widely separated views. These environments exhibit often shadows, lack textured areas, or contain repetitive textures which multiply the ambiguities in standard computer vision pipelines. During my talk I [&hellip;]<\/p>\n","protected":false},"featured_media":194563,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-182323","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/4XWIrE5gSqE","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/182323"}],"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\/182323\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/194563"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=182323"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=182323"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=182323"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=182323"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=182323"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=182323"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}