Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching

TL;DR

This paper introduces a novel unsupervised stereo matching framework that leverages disparity confidence estimation and depth priors to improve accuracy, especially in ambiguous regions, achieving state-of-the-art results on KITTI benchmarks.

Contribution

It proposes a plug-and-play disparity confidence estimation method and depth prior-guided loss functions to enhance unsupervised stereo matching.

Findings

Achieves state-of-the-art accuracy on KITTI benchmarks.

Effectively handles ambiguous regions like repetitive patterns and texture-less areas.

Improves disparity estimation by utilizing confident disparity and depth information.

Abstract

Unsupervised stereo matching has garnered significant attention for its independence from costly disparity annotations. Typical unsupervised methods rely on the multi-view consistency assumption for training networks, which suffer considerably from stereo matching ambiguities, such as repetitive patterns and texture-less regions. A feasible solution lies in transferring 3D geometric knowledge from a relative depth map to the stereo matching networks. However, existing knowledge transfer methods learn depth ranking information from randomly built sparse correspondences, which makes inefficient utilization of 3D geometric knowledge and introduces noise from mistaken disparity estimates. This work proposes a novel unsupervised learning framework to address these challenges, which comprises a plug-and-play disparity confidence estimation algorithm and two depth prior-guided loss functions. Specifically, the local coherence consistency between neighboring disparities and their corresponding relative depths is first checked to obtain disparity confidence. Afterwards, quasi-dense correspondences are built using only confident disparity estimates to facilitate efficient depth ranking learning. Finally, a dual disparity smoothness loss is proposed to boost stereo matching performance at disparity discontinuities. Experimental results demonstrate that our method achieves state-of-the-art stereo matching accuracy on the KITTI Stereo benchmarks among all unsupervised stereo matching methods.