Abstract
Occlusion boundaries contain rich perceptual informa-tion about the underlying scene structure. They also pro-vide important cues in many visual perception tasks such asscene understanding, object recognition, and segmentation.In this paper, we improve occlusion boundary detection viaenhanced exploration of contextual information (e.g., localstructural boundary patterns, observations from surround-ing regions, and temporal context), and in doing so developa novel approach based on convolutional neural networks(CNNs) and conditional random fields (CRFs). Experimental results demonstrate that our detector significantly outperforms the state-of-the-art (e.g., improving the F-measurefrom 0.62 to 0.71 on the commonly used CMU benchmark).Last but not least, we empirically assess the roles of several important components of the proposed detector, so as to validate the rationale behind this approach.