SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
2021-05-14CVPR 2021Code Available1· sign in to hype
Austin Stone, Daniel Maurer, Alper Ayvaci, Anelia Angelova, Rico Jonschkowski
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/google-research/google-research/tree/master/smurfOfficialjax★ 0
- github.com/ChristophReich1996/SMURFpytorch★ 21
- github.com/MindSpore-scientific/code-14/tree/main/smumindspore★ 0
Abstract
We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by 36\% to 40\% (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2. Our method integrates architecture improvements from supervised optical flow, i.e. the RAFT model, with new ideas for unsupervised learning that include a sequence-aware self-supervision loss, a technique for handling out-of-frame motion, and an approach for learning effectively from multi-frame video data while still only requiring two frames for inference.