Sökning: onr:"swepub:oai:lup.lub.lu.se:0bbd40f9-5373-4cdf-a789-03f470b97e46" > In Defense of 3D-La...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 02982naa a2200349 4500 | |
001 | oai:lup.lub.lu.se:0bbd40f9-5373-4cdf-a789-03f470b97e46 | |
003 | SwePub | |
008 | 160401s2013 | |||||||||||000 ||eng| | |
024 | 7 | a https://lup.lub.lu.se/record/39147992 URI |
024 | 7 | a https://doi.org/10.1109/CVPR.2013.2262 DOI |
040 | a (SwePub)lu | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a kon2 swepub-publicationtype |
072 | 7 | a ref2 swepub-contenttype |
100 | 1 | a Olsson, Carlu Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH4 aut0 (Swepub:lu)math-coo |
245 | 1 0 | a In Defense of 3D-Label Stereo |
264 | 1 | c 2013 |
300 | a 8 s. | |
520 | a It is commonly believed that higher order smoothness should be modeled using higher order interactions. For example, 2nd order derivatives for deformable (active) contours are represented by triple cliques. Similarly, the 2nd order regularization methods in stereo predominantly use MRF models with scalar (1D) disparity labels and triple clique interactions. In this paper we advocate a largely overlooked alternative approach to stereo where 2nd order surface smoothness is represented by pairwise interactions with 3D-labels, e.g. tangent planes. This general paradigm has been criticized due to perceived computational complexity of optimization in higher-dimensional label space. Contrary to popular beliefs, we demonstrate that representing 2nd order surface smoothness with 3D labels leads to simpler optimization problems with (nearly) submodular pairwise interactions. Our theoretical and experimental results demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Datorseende och robotik0 (SwePub)102072 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Computer Vision and Robotics0 (SwePub)102072 hsv//eng |
650 | 7 | a NATURVETENSKAPx Matematik0 (SwePub)1012 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Mathematics0 (SwePub)1012 hsv//eng |
700 | 1 | a Ulén, Johannesu Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH4 aut0 (Swepub:lu)math-jsu |
700 | 1 | a Boykov, Yuri4 aut |
710 | 2 | a Matematik LTHb Matematikcentrum4 org |
773 | 0 | t Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference ong , s. 1730-1737q <1730-1737x 1063-6919x 2163-6648 |
856 | 4 | u http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619070y FULLTEXT |
856 | 4 | u http://dx.doi.org/10.1109/CVPR.2013.226y FULLTEXT |
856 | 4 8 | u https://lup.lub.lu.se/record/3914799 |
856 | 4 8 | u https://doi.org/10.1109/CVPR.2013.226 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.