Variational multi-image stereo matching

In two-view stereo matching, the disparity of occluded pixels cannot accurately be estimated directly: it needs to be inferred through, e.g., regularisation. When capturing scenes using a plenoptic camera or a camera dolly on a track, more than two input images are available, and - contrary to the two-view case -pixels in the central view will only very rarely be occluded in all of the other views. By explicitly handling occlusions, we can limit the depth estimation of pixel (P) over right arrow to only use those cameras that actually observe (p) over right arrow. We do this by extending variational stereo matching to multiple views, and by explicitly handling occlusion on a view-by-view basis. Resulting depth maps are illustrated to be sharper and less noisy than typical recent techniques working on light fields.In two-view stereo matching, the disparity of occluded pixels cannot accurately be estimated directly: it needs to be inferred through, e.g., regularisation. When capturing scenes using a plenoptic camera or a camera dolly on a track, more than two input images are available, and - contrary to the two-view case -pixels in the central view will only very rarely be occluded in all of the other views. By explicitly handling occlusions, we can limit the depth estimation of pixel (P) over right arrow to only use those cameras that actually observe (p) over right arrow. We do this by extending variational stereo matching to multiple views, and by explicitly handling occlusion on a view-by-view basis. Resulting depth maps are illustrated to be sharper and less noisy than typical recent techniques working on light fields.P