000128390 001__ 128390
000128390 005__ 20190812205235.0
000128390 037__ $$aCONF
000128390 245__ $$aCombined Depth and Outlier Estimation in Multi-View Stereo
000128390 260__ $$c2006
000128390 269__ $$a2006
000128390 336__ $$aConference Papers
000128390 520__ $$aIn this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes: (i) an inlier process, which generates the pixels which are visible from the reference camera and which obey the constant brightness assumption, and (ii) an outlier process which generates all other pixels. Depth and visibility are jointly modelled as a hiddenMarkov Random Field, and the spatial correlations of both are explicitly accounted for. Inference is made tractable by an EM-algorithm, which alternates between estimation of visibility and depth, and optimisation of model parameters. We describe and compare two implementations of the E-step of the algorithm, which correspond to the Mean Field and Bethe approximations of the free energy. The approach is validated by experiments on challenging real-world scenes, of which two are contaminated by independently moving objects.
000128390 700__ $$0244088$$g182325$$aStrecha, Christoph
000128390 700__ $$aFransens, Rik
000128390 700__ $$aVan Gool, Luc
000128390 7112_ $$dJune 17-22, 2006$$cNew York$$aIEEE Conference on Computer Vision and Pattern Recognition
000128390 773__ $$tProceedings of the IEEE Conference on Computer Vision and Pattern Recognition
000128390 8564_ $$zURL$$uhttp://www.cvpr.org/2006/
000128390 8564_ $$zn/a$$uhttps://infoscience.epfl.ch/record/128390/files/cvpr_2006.pdf$$s482051
000128390 909C0 $$xU10659$$pCVLAB$$0252087
000128390 909CO $$ooai:infoscience.tind.io:128390$$qGLOBAL_SET$$pconf$$pIC
000128390 937__ $$aCVLAB-CONF-2008-017
000128390 973__ $$rREVIEWED$$sPUBLISHED$$aOTHER
000128390 980__ $$aCONF