Large Occlusion Completion Using Normal Maps

Dense disparity maps can be computed from wide-baseline stereo pairs but will inevitably contain large areas where the depth cannot be estimated accurately because the pixels are seen in one view only. A traditional approach to this problem is to introduce a global optimization scheme to fill-in the missing information by enforcing spatialconsistency, which usually means introducing a geometric regularization term that promotes smoothness. The world, however, is not necessarily smooth and we argue that a better approach is to monocularly estimate the surface normals and to use them to supply the required constraints. We will show that, even though the estimates are very rough, we nevertheless obtain more accurate depth-maps than by enforcing smoothness. Furthermore, this can be done effectively by solving large but sparse linear systems.