5 papers with code • 0 benchmarks • 0 datasets
These leaderboards are used to track progress in Occlusion Estimation
We introduce a compact network for holistic scene flow estimation, called SENSE, which shares common encoder features among four closely-related tasks: optical flow estimation, disparity estimation from stereo, occlusion estimation, and semantic segmentation.
The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images.
The key idea of the proposed approach is to estimate the dense cross-domain correspondence between the sketch and cartoon video frames, and employ a blending module with occlusion estimation to synthesize the middle frame guided by the sketch.
Labeled real data of occlusions is scarce (even in large datasets) and synthetic data leaves a domain gap, making it hard to explicitly model and learn occlusions.