English

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping

Computer Vision and Pattern Recognition 2021-05-18 v1

Abstract

We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by 36%36\% to 40%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.

Keywords

Cite

@article{arxiv.2105.07014,
  title  = {SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping},
  author = {Austin Stone and Daniel Maurer and Alper Ayvaci and Anelia Angelova and Rico Jonschkowski},
  journal= {arXiv preprint arXiv:2105.07014},
  year   = {2021}
}

Comments

Accepted at CVPR 2021, all code available at https://github.com/google-research/google-research/tree/master/smurf

R2 v1 2026-06-24T02:07:38.917Z