Figure 6From: Layer-based sparse representation of multiview imagesLayer from the animal farm dataset. (a) The unoccluded layer ℋ k can be defined using the contour γ k (s) on one viewpoint projected to the remaining frames. The 2D contour is denoted by the red curve on the first image. (b) Occluded layer ℋ k V can be inferred by removing the regions which intersect with other layers related to a smaller depth.Back to article page