Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
This work addresses occlusion estimation for computer vision tasks like disparity and optical flow, which is important for applications such as autonomous driving and robotics, but it appears incremental as it builds on existing learning-based approaches.
The paper tackles the problem of estimating occlusions jointly with disparities or optical flow to improve depth and motion boundary detection, resulting in state-of-the-art performance on the KITTI benchmark and enhanced motion segmentation and scene flow estimation.
Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.