Self-supervised monocular depth estimation usually assumes that training samples contain only static objects, which leads to poor performance in real-world environments. The presence of dynamic objects incurs camera motion estimation errors, motion blur, and occlusions, which induce significant challenges for network training. To address these issues, we introduce EDS-Depth, a self-supervised learning framework, that improves monocular depth estimation in dynamic scenes. Firstly, we propose a novel TCE (Temporal Continuity Enhancement) strategy to reduce camera motion estimation errors and motion blur caused by dynamic objects. Video frames are interpolated to generate more continuous frames in order to smooth dynamic changes and enrich motion details. Secondly, we design a novel IPDM (Iterative Pseudo Depth Masking) module to address inaccurate object motion and occlusions in dynamic scenes. The module integrates multiple optical flows from different frames for triangulation, generating optimal depth as pseudo-supervision labels in dynamic regions. Extensive experiments on Cityscapes and KITTI datasets demonstrate the effectiveness of EDS-Depth, which surpasses state-of-the-art self-supervised monocular depth estimation methods, particularly in dynamic scenes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Beteiligte:
    Yu, Shangshu (Autor:in) / Wu, Meiqing (Autor:in) / Lam, Siew-Kei (Autor:in) / Wang, Changshuo (Autor:in) / Wang, Ruiping (Autor:in)


    Erscheinungsdatum :

    01.04.2025


    Format / Umfang :

    4076409 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LAM-Depth: Laplace-Attention Module-Based Self-Supervised Monocular Depth Estimation

    Wei, Jiansheng / Pan, Shuguo / Gao, Wang et al. | IEEE | 2024


    Real-Time Self-Supervised Monocular Depth Estimation Without GPU

    Poggi, Matteo / Tosi, Fabio / Aleotti, Filippo et al. | IEEE | 2022


    A Self-Supervised Monocular Depth Estimation Approach Based on UAV Aerial Images

    Zhang, Yuhang / Yu, Qing / Low, Kin Huat et al. | IEEE | 2022


    Self-Supervised Monocular Depth Estimation With Geometric Prior and Pixel-Level Sensitivity

    Liu, Jierui / Cao, Zhiqiang / Liu, Xilong et al. | IEEE | 2023


    Self-occlusion masks to improve self-supervised monocular depth estimation in multi-camera settings

    GUIZILINI VITOR / AMBRUS RARES ANDREI / GAIDON ADRIEN DAVID et al. | Europäisches Patentamt | 2024

    Freier Zugriff