When handling occlusion in unsupervised stereo matching, existing methods tend to neglect the supportive role of occlusion and to perform inappropriate disparity smoothing around the occlusion. To address these problems, we propose an occlusion-aware stereo network that contains a specific module to first estimate occlusion as an additional depth cue. In the occlusion inference module, a pixel is classified with a three-category label based on whether an area is occluded by an object on the left, occluded by an object on the right, or unoccluded. After the occluders are detected, we introduce a directed disparity smoothing loss that allows valid disparity estimates to be propagated to fill the occluded region, while ambiguous matches in the occluded region do not affect other regions. Disparity and occlusion are trained alternately in an unsupervised manner with detached backpropagation to enable the directed smoothness. Experiments show that our method achieves 3-pixel threshold error rates of 6.51% and 5.69% on the KITTI 2015 and KITTI 2012 validation sets, state-of-the-art results among unsupervised learning networks at the time of submission.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unsupervised Occlusion-Aware Stereo Matching With Directed Disparity Smoothing


    Contributors:
    Li, Ang (author) / Yuan, Zejian (author) / Ling, Yonggen (author) / Chi, Wanchao (author) / Zhang, Shenghao (author) / Zhang, Chong (author)


    Publication date :

    2022-07-01


    Size :

    2770999 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Occlusion-Aware Stereo Matching

    Xu, J. / Yang, Q. / Feng, Z. | British Library Online Contents | 2016


    Stereo Feature Matching in Disparity Space

    Braunegg, David J. | DSpace@MIT | 1989

    Free access

    Dense Stereo Matching in Restricted Disparity Space

    Hattori, H. / Takeda, N. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2005


    Dense stereo matching in restricted disparity space

    Hattori, H. / Takeda, N. | IEEE | 2005


    Disparity refinement with stability-based tree for stereo matching

    Ji, Yuhang / Zhang, Qieshi / Sugimoto, Kenjiro et al. | IEEE | 2015