Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes
This work addresses optical flow estimation for computer vision applications, offering an incremental improvement by integrating geometric constraints into unsupervised learning.
The paper tackles the problem of optical flow estimation in unsupervised deep learning by incorporating global geometric constraints, specifically epipolar constraints, to address performance degradation in repetitive textures or occlusions, achieving competitive performance with supervised methods and outperforming state-of-the-art unsupervised methods on various datasets.
Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance degrades at regions where repetitive textures or occlusions occur. In this paper, we propose Deep Epipolar Flow, an unsupervised optical flow method which incorporates global geometric constraints into network learning. In particular, we investigate multiple ways of enforcing the epipolar constraint in flow estimation. To alleviate a "chicken-and-egg" type of problem encountered in dynamic scenes where multiple motions may be present, we propose a low-rank constraint as well as a union-of-subspaces constraint for training. Experimental results on various benchmarking datasets show that our method achieves competitive performance compared with supervised methods and outperforms state-of-the-art unsupervised deep-learning methods.