Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions and moving objects in a scene violate the underlying static scenario assumption. In addition, pixels in textureless regions or less discriminative pixels hinder model training. To address these problems, in this paper, we deal with moving objects and occlusions by utilizing the differences between the flow fields, and the differences between the depth structure generated by affine transformation and view synthesis, respectively. Secondly, we mitigate the effect of textureless regions on model optimization by measuring the differences between features with more semantic and contextual information without requiring additional networks. In addition, although the bidirectionality component is used in each sub-objective function, a pair of images is reasoned about only once, which helps reduce overhead. Extensive experiments and visual analysis demonstrate the effectiveness of the proposed method, which outperforms existing state-of-the-art self-supervised methods under the same conditions and without introducing additional auxiliary information.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    CbwLoss: Constrained Bidirectional Weighted Loss for Self-Supervised Learning of Depth and Pose


    Contributors:
    Wang, Fei (author) / Cheng, Jun (author) / Liu, Penglei (author)


    Publication date :

    2023-06-01


    Size :

    6796119 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    PHOTOMETRIC MASKS FOR SELF-SUPERVISED DEPTH LEARNING

    GUIZILINI VITOR | European Patent Office | 2024

    Free access

    Constrained Optimization for Human Pose Estimation from Depth Sequences

    Zhu, Youding / Fujimura, Kikuo | Springer Verlag | 2007


    SELF EXTRINSIC SELF-CALIBRATION VIA GEOMETRICALLY CONSISTENT SELF-SUPERVISED DEPTH AND EGO-MOTION LEARNING

    KANAI TAKAYUKI / CAMPAGNOLO GUIZILINI VITOR / AMBRUS RARES A et al. | European Patent Office | 2025

    Free access


    EDS-Depth: Enhancing Self-Supervised Monocular Depth Estimation in Dynamic Scenes

    Yu, Shangshu / Wu, Meiqing / Lam, Siew-Kei et al. | IEEE | 2025