Stereo matching aims to perceive the 3D geometric configuration of scenes and facilitates a variety of computer vision in advanced driver assistance systems (ADAS) applications. Recently, deep convolutional neural networks (CNNs) have shown dramatic performance improvements for computing the matching cost in the stereo matching. However, the performance of CNN-based approaches relies heavily on datasets, requiring a large number of ground truth data which needs tremendous works. To overcome this limitation, we present a novel framework to learn CNNs for matching cost computation in an unsupervised manner. Our method leverages an image domain learning combined with stereo epipolar constraints. By exploiting the correspondence consistency between stereo images, our method selects putative positive samples in each training iteration and utilizes them to train the networks. We further propose a positive sample propagation scheme to leverage additional training samples. Our unsupervised learning method is evaluated with two kinds of network architectures, simple and precise CNNs, and shows comparable performance to that of the state-of-the-art methods including both supervised and unsupervised learning approaches on KITTI, Middlebury, HCI, and Yonsei datasets. This extensive evaluation demonstrates that the proposed learning framework can be applied to deal with various real driving conditions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unsupervised Stereo Matching Using Confidential Correspondence Consistency


    Contributors:


    Publication date :

    2020-05-01


    Size :

    9880113 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Unsupervised Occlusion-Aware Stereo Matching With Directed Disparity Smoothing

    Li, Ang / Yuan, Zejian / Ling, Yonggen et al. | IEEE | 2022



    Fast Stereo Matching Using Reliability-Based Dynamic Programming and Consistency Constraints

    Gong, M. / Yang, H. / IEEE | British Library Conference Proceedings | 2003


    Adaptive Cost Volume Representation for Unsupervised High-Resolution Stereo Matching

    Tong, Wei / Sun, Zhao-Hui / Wu, Edmond et al. | IEEE | 2023


    Efficient interscanline consistency enforcing method for dynamic programming-based dense stereo matching algorithms

    Salehian, B. / Raie, A.A. / Fotouhi, A.M. et al. | British Library Online Contents | 2013