UnDAF: A General Unsupervised Domain Adaptation Framework for Disparity or Optical Flow Estimation
Hengli Wang,Rui Fan,Peide Cai,Ming Liu,Lujia Wang,Hengli Wang,Rui Fan,Peide Cai,Ming Liu,Lujia Wang
Disparity and optical flow estimation are respectively 1D and 2D dense correspondence matching (DCM) tasks in nature. Unsupervised domain adaptation (UDA) is crucial for their success in new and unseen scenarios, enabling networks to draw inferences across different domains without manually-labeled ground truth. In this paper, we propose a general UDA framework (UnDAF) for disparity or optical flo...
