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

Autor:	Stone, Austin, Maurer, Daniel, Ayvaci, Alper, Angelova, Anelia, Jonschkowski, Rico
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted at CVPR 2021, all code available at https://github.com/google-research/google-research/tree/master/smurf
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2105.07014 Zobrazit plný text záznamu View this record from Arxiv