OccInpFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning
This addresses occlusion handling in optical flow estimation for computer vision applications, representing an incremental advance over existing methods.
The paper tackles the problem of occlusion in unsupervised optical flow estimation by proposing an occlusion-inpainting framework that utilizes occlusion regions for learning, resulting in significant performance improvements on benchmarks like Flying Chairs, KITTI, and MPI-Sintel.
Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can provide effective information for optical flow learning. In this paper, we present OccInpFlow, an occlusion-inpainting framework to make full use of occlusion regions. Specifically, a new appearance-flow network is proposed to inpaint occluded flows based on the image content. Moreover, a boundary warp is proposed to deal with occlusions caused by displacement beyond image border. We conduct experiments on multiple leading flow benchmark data sets such as Flying Chairs, KITTI and MPI-Sintel, which demonstrate that the performance is significantly improved by our proposed occlusion handling framework.