{"id":1738,"date":"2010-11-29T15:03:17","date_gmt":"2010-11-29T15:03:17","guid":{"rendered":"http:\/\/hgpu.org\/?p=1738"},"modified":"2010-11-29T15:03:17","modified_gmt":"2010-11-29T15:03:17","slug":"multi-camera-real-time-depth-estimation-with-discontinuity-handling-on-pc-graphics-hardware","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=1738","title":{"rendered":"Multi-camera real-time depth estimation with discontinuity handling on PC graphics hardware"},"content":{"rendered":"<p>This paper describes a system for dense depth estimation from multiple color images in real-time. Our algorithm runs almost entirely on standard graphics hardware, leaving the main CPU free for other tasks such as image capture and higher level recognition. We follow a plane-sweep approach extended by truncated SSD scores, spatially shiftable windows and best camera selection to handle discontinuities. We do not need specialized hardware and exploit the computational power of freely programmable PC GPU hardware. Dense depth maps are computed with up to 20 fps.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This paper describes a system for dense depth estimation from multiple color images in real-time. Our algorithm runs almost entirely on standard graphics hardware, leaving the main CPU free for other tasks such as image capture and higher level recognition. We follow a plane-sweep approach extended by truncated SSD scores, spatially shiftable windows and best [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[73,33,3],"tags":[444,1791,1786,20],"class_list":["post-1738","post","type-post","status-publish","format-standard","hentry","category-computer-vision","category-image-processing","category-paper","tag-cg","tag-computer-vision","tag-image-processing","tag-nvidia"],"views":1985,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1738","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1738"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1738\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1738"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1738"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1738"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}