Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation

arXiv:2212.05315v3 Announce Type: replace
Abstract: Monocular Depth Estimation (MDE) is a fundamental problem in computer vision with numerous applications. Recently, LIDAR-supervised methods have achieved remarkable per-pixel depth accuracy in outdoor scenes. However, significant errors are typically found in the proximity of depth discontinuities, i.e., depth edges, which often hinder the performance of depth-dependent applications that are sensitive to such inaccuracies, e.g., novel view synthesis and augmented reality. Since direct supervision for the location of depth edges is typically unavailable in …

arxiv cs.cv edge mind the edge type