FAST Depth Completion using a view Constrained Deep Prior

We extend the DIP concept to apply to depth images. Given color images and noisy and incomplete target depth maps, we optimize a randomly-initialized CNN model to reconstruct an depth map restored by virtue of using the CNN network structure as a prior combined with a view-constrained photo-consistency loss, which is computed using images from a geometrically calibrated camera from nearby viewpoints. We apply this deep depth prior for inpainting and refining incomplete and noisy depth maps within both binocular and multi-view stereo pipelines.