"Segmentation Based Multi-View Stereo"@en . "978-3-200-01390-2" . "21230" . . "Jan\u010Do\u0161ek, Michal" . "340549" . . "Segmentation Based Multi-View Stereo"@en . "Wien" . "Pajdla, Tom\u00E1\u0161" . "6"^^ . "Pattern Recognition & Image Processing Group, Vienna University of Technology" . . . "2"^^ . . . "RIV/68407700:21230/09:00163118!RIV10-MSM-21230___" . . . "2"^^ . . "Segmentation Based Multi-View Stereo" . "RIV/68407700:21230/09:00163118" . "This paper presents a segmentation based multiview stereo reconstruction method. We address (i) dealing with uninformative texture in very homogeneous image areas and (ii) processing of large images in affordable time. To avoid searching for optimal surface position and orientation based on uninformative texture, we (over)segment images into segments of low variation of color and intensity and use each segment to generate a candidate 3D planar patch explaining the underlying 3D surface. Every point of the surface is explained by multiple candidate patches generated from image segments from different images. Observing that the correctly reconstructed surface is consistently generated from different images, the candidates that do not have consistent support by other candidates from other images are rejected. This approach leads to stable and good results."@en . . "computer vision; surface reconstruction"@en . . "[E908D27EFEA0]" . "Segmentation Based Multi-View Stereo" . . "2009-02-04+01:00"^^ . "S" . . . . "Eibiswald" . "This paper presents a segmentation based multiview stereo reconstruction method. We address (i) dealing with uninformative texture in very homogeneous image areas and (ii) processing of large images in affordable time. To avoid searching for optimal surface position and orientation based on uninformative texture, we (over)segment images into segments of low variation of color and intensity and use each segment to generate a candidate 3D planar patch explaining the underlying 3D surface. Every point of the surface is explained by multiple candidate patches generated from image segments from different images. Observing that the correctly reconstructed surface is consistently generated from different images, the candidates that do not have consistent support by other candidates from other images are rejected. This approach leads to stable and good results." . "CVWW 2009: Computer Vision Winter Workshop 2009" .