Co-Teaching: An Ark to Unsupervised Stereo Matching
arXiv:2107.08186
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.
5 pages, 3 figures and 2 tables. This paper is accepted by ICIP 2021
References in corpus (4)
- SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
- Self-Supervised Learning for Stereo Matching with Self-Improving Ability
- Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
- Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation