SplatFlow: Learning Multi-frame Optical Flow via Splatting

arXiv:2306.08887v2 Announce Type: replace
Abstract: The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggle to handle occlusions; in particular, those based on two frames cannot correctly handle occlusions because occluded regions have no visual correspondences. However, there is still hope in multi-frame settings, which can potentially mitigate the occlusion issue in OFE. Unfortunately, multi-frame OFE (MOFE) remains underexplored, and …

arxiv cs.cv flow optical optical flow type via