{"id":1737,"date":"2010-11-29T15:03:16","date_gmt":"2010-11-29T15:03:16","guid":{"rendered":"http:\/\/hgpu.org\/?p=1737"},"modified":"2010-11-29T15:03:16","modified_gmt":"2010-11-29T15:03:16","slug":"real-time-multi-stereo-depth-estimation-on-gpu-with-approximative-discontinuity-handling","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=1737","title":{"rendered":"Real-time multi-stereo depth estimation on GPU with approximative discontinuity handling"},"content":{"rendered":"<p>This paper describes a system for dense depth estimation for multiple images in real-time. The algorithm runs almost entirely on standard graphics hardware, leaving the main CPU free for other tasks as image capture, compression and storage during scene capture. We follow a plain-sweep approach extended by truncated SSD scores, shiftable windows and best camera selection. We do not need specialized hardware and exploit the computational power of freely programmable PC graphics 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 for multiple images in real-time. The algorithm runs almost entirely on standard graphics hardware, leaving the main CPU free for other tasks as image capture, compression and storage during scene capture. We follow a plain-sweep approach extended by truncated SSD scores, shiftable windows and best camera [&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":[444,1791,1786,20,875],"class_list":["post-1737","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","tag-nvidia-geforce-fx-5600"],"views":2093,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1737","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=1737"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1737\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}