Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules to capture the spatial and temporal relations accordingly. More Specifically, intra-frame relation module (IntraRM) encapsulates the intra-frame objects into a sparse graph and thus allows us to refine the object features through efficient message passing. On the other hand, inter-frame relation module (InterRM) densely connects each object in its corresponding tracked sequences dynamically, and leverages such temporal information to further enhance its representations efficiently through a lightweight transformer network. We instantiate our novel designs of IntraRM and InterRM with general center-based or anchor-based detectors and evaluate them on Waymo Open Dataset (WOD). With negligible extra overhead, Ret3D achieves the state-of-the-art performance, being 5.5% and 3.2% higher than the recent competitor in terms of the LEVEL 1 and LEVEL 2 mAPH metrics on vehicle detection, respectively.


    Access

    Download


    Export, share and cite



    Title :

    Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes


    Contributors:
    Wu, Y. (author) / Zhang, D. (author) / Zhang, L. (author) / Zhan, X. (author) / Dai, D. (author) / Liu, Y. (author) / Cheng, M. (author)

    Publication date :

    2022-01-01


    Type of media :

    Paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629




    Understanding object relations in traffic scenes

    Hensel, Irina / Bachmann, Alexander / Hummel, Britta et al. | Tema Archive | 2010


    Bayesian object detection in dynamic scenes

    Sheikh, Y. / Shah, M. | IEEE | 2005


    Robust 3D Object Detection Based on Point Feature Enhancement in Driving Scenes

    Chen, Renjie / Zhang, Dongbo / Liu, Qinrui et al. | IEEE | 2024


    Uncertainty-Aware and Class-Balanced Domain Adaptation for Object Detection in Driving Scenes

    Cai, Minjie / Kezierbieke, Jianaresi / Zhong, Xionghu et al. | IEEE | 2024


    Object Detection-based Visual SLAM for Dynamic Scenes

    Zhao, Xinhua / Ye, Lei | British Library Conference Proceedings | 2022