Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes

TL;DR

This paper introduces Deep Epipolar Flow, an unsupervised deep learning approach for optical flow that incorporates global geometric constraints, improving performance especially in challenging regions with textures or occlusions.

Contribution

It proposes a novel unsupervised optical flow method that integrates epipolar constraints and low-rank or union-of-subspaces constraints to handle dynamic scenes effectively.

Findings

Achieves competitive results with supervised methods

Outperforms existing unsupervised deep-learning approaches

Effective in scenes with repetitive textures or occlusions

Abstract

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.