OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow
This work addresses accuracy issues in optical flow for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled the problems of ghosting from warping and equal treatment of occluded regions in optical flow estimation by proposing OAS-Net, which uses a sampling-based correlation layer and an occlusion-aware module, achieving effective results on Sintel and KITTI datasets.
Optical flow estimation is an essential step for many real-world computer vision tasks. Existing deep networks have achieved satisfactory results by mostly employing a pyramidal coarse-to-fine paradigm, where a key process is to adopt warped target feature based on previous flow prediction to correlate with source feature for building 3D matching cost volume. However, the warping operation can lead to troublesome ghosting problem that results in ambiguity. Moreover, occluded areas are treated equally with non occluded regions in most existing works, which may cause performance degradation. To deal with these challenges, we propose a lightweight yet efficient optical flow network, named OAS-Net (occlusion aware sampling network) for accurate optical flow. First, a new sampling based correlation layer is employed without noisy warping operation. Second, a novel occlusion aware module is presented to make raw cost volume conscious of occluded regions. Third, a shared flow and occlusion awareness decoder is adopted for structure compactness. Experiments on Sintel and KITTI datasets demonstrate the effectiveness of proposed approaches.