Revisiting depth layers from occlusions

In this work, we consider images of a scene with a moving object captured by a static camera. As the ob-ject (human or otherwise) moves about the scene, it re-veals pairwise depth-ordering or occlusion cues. The goal of this work is to use these sparse occlusion cues along with monocular depth occlusion cues to densely segment the scene into depth layers. We cast the problem of depth-layer segmentation as a discrete labeling problem on a spatio-temporal Markov Random Field (MRF) that uses the motion occlusion cues along with monocular cues and a smooth motion prior for the moving object. We quantitatively show that depth ordering produced by the proposed combination of the depth cues from object motion and monocular occlu-sion cues are superior to using either feature independently, and using a naı̈ve combination of the features. 1