-
[pdf]
[arXiv]
[bibtex]@InProceedings{Stone_2021_CVPR, author = {Stone, Austin and Maurer, Daniel and Ayvaci, Alper and Angelova, Anelia and Jonschkowski, Rico}, title = {SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {3887-3896} }
SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping
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% 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 novel unsupervised sequence loss and 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.
Related Material