U$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation

ArXi:2604.10056v1 Announce Type: new Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates optical flow and per-pixel uncertainty. The core innovation is a decoupled learning strategy that derives uncertainty supervision from augmentation consistency via a Laplace-based maximum likelihood objective, enabling stable