English

Co-Teaching: An Ark to Unsupervised Stereo Matching

Computer Vision and Pattern Recognition 2021-07-20 v1 Robotics

Abstract

Stereo matching is a key component of autonomous driving perception. Recent unsupervised stereo matching approaches have received adequate attention due to their advantage of not requiring disparity ground truth. These approaches, however, perform poorly near occlusions. To overcome this drawback, in this paper, we propose CoT-Stereo, a novel unsupervised stereo matching approach. Specifically, we adopt a co-teaching framework where two networks interactively teach each other about the occlusions in an unsupervised fashion, which greatly improves the robustness of unsupervised stereo matching. Extensive experiments on the KITTI Stereo benchmarks demonstrate the superior performance of CoT-Stereo over all other state-of-the-art unsupervised stereo matching approaches in terms of both accuracy and speed. Our project webpage is https://sites.google.com/view/cot-stereo.

Keywords

Cite

@article{arxiv.2107.08186,
  title  = {Co-Teaching: An Ark to Unsupervised Stereo Matching},
  author = {Hengli Wang and Rui Fan and Ming Liu},
  journal= {arXiv preprint arXiv:2107.08186},
  year   = {2021}
}

Comments

5 pages, 3 figures and 2 tables. This paper is accepted by ICIP 2021

R2 v1 2026-06-24T04:16:53.841Z