MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching

TL;DR

MC-Stereo introduces a novel iterative stereo matching framework that effectively handles multi-peak distributions and employs a cascade search range, achieving state-of-the-art results on major benchmarks.

Contribution

The paper proposes MC-Stereo, a new iterative optimization architecture with multi-peak lookup and cascade search range, plus a pre-trained feature extractor, advancing stereo matching accuracy.

Findings

Ranks first on KITTI-2012 and KITTI-2015 benchmarks.

Achieves state-of-the-art performance on ETH3D.

Effectively handles multi-peak distributions in stereo matching.

Abstract

Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which struggles to handle the multi-peak problem effectively. Additionally, the fixed search range used during the iteration process limits the final convergence effects. To address these issues, we present a novel iterative optimization architecture called MC-Stereo. This architecture mitigates the multi-peak distribution problem in matching through the multi-peak lookup strategy, and integrates the coarse-to-fine concept into the iterative framework via the cascade search range. Furthermore, given that feature representation learning is crucial for successful learn-based stereo matching, we introduce a pre-trained network to serve as the feature extractor, enhancing the front end of the stereo matching pipeline. Based on these improvements, MC-Stereo ranks first among all publicly available methods on the KITTI-2012 and KITTI-2015 benchmarks, and also achieves state-of-the-art performance on ETH3D. Code is available at https://github.com/MiaoJieF/MC-Stereo.