Monocular relative depth reordering by propagating confidence of local and global cues

摘要

Local occlusion cue has been successfully exploited to infer depth ordering from monocular image. However, due to uncertainty of occluded relations, inconsistent results frequently arise, especially for the image of complex scenarios. We propose a depth propagation mechanism which incorporates local occlusion and global ground cues together in the way of probabilistic-to-energetic Bayesian framework. By maximizing posterior namely minimizing energy of latent relative depth variables with well-defined pairwise occlusion priori, we recover correct depth ordering in monocular setting. Our model can guarantee the consistency of relative depth labeling in automatically constructed topological graph via transferring more confident aligned multi-depth cues amongst different segments. Experiments demonstrate that more reasonable and accurate outcomes can be achieved by our depth propagation mechanism and they are also superior to common-used occlusion-based approaches in complex nature.