StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation
This addresses the challenge of domain shift in computer vision tasks for researchers and practitioners, though it is incremental as it builds on existing domain adaptation techniques.
The paper tackled the problem of training stereo matching and optical flow models for real images using only synthetic ground-truth data, achieving competitive performance over previous domain translation-based methods.
We introduce a novel training strategy for stereo matching and optical flow estimation that utilizes image-to-image translation between synthetic and real image domains. Our approach enables the training of models that excel in real image scenarios while relying solely on ground-truth information from synthetic images. To facilitate task-agnostic domain adaptation and the training of task-specific components, we introduce a bidirectional feature warping module that handles both left-right and forward-backward directions. Experimental results show competitive performance over previous domain translation-based methods, which substantiate the efficacy of our proposed framework, effectively leveraging the benefits of unsupervised domain adaptation, stereo matching, and optical flow estimation.