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

• Published in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3886 - 3895
• Main Authors: Stone, Austin, Maurer, Daniel, Ayvaci, Alper, Angelova, Anelia, Jonschkowski, Rico
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2021
• Subjects: Benchmark testing; Computational modeling; Computer architecture; Computer vision; Data models; Estimation; Optical losses

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...