LiDAR has become one of the primary 3D object detection sensors in autonomous driving. However, due to the inherent sparsity of point clouds, certain objects exhibit structure incompleteness in occluded and distant areas, which hampers the accurate perception of objects in 3D space. To tackle this challenge, we propose Semantic and Structure Completion Network (S2CNet) for 3D object detection. Concretely, we design the Semantic Completion (SeC) module to generate semantic features in Bird’s-Eye-View (BEV) space, utilizing a teacher-student paradigm. Notably, we adopt a coarse-to-fine guidance strategy to encourage student network to generate semantic features specifically within foreground regions. This ensures that the student network focuses on the generation of foreground object features. Besides, we introduce an attention-based module to adaptively fuse the generated features and raw features. SeC module faces particular limitation when dealing with objects containing only a few points, in such case, the network is prone to generating low quality proposals with inaccurate localization. Complementary to SeC module, we introduce the Structure Completion (StC) module, in which a group of structural proposals are obtained by traversing most structures in a structure-guided manner, and thus at least one proposal with ground truth similar structure can be guaranteed. Extensive experiments on the KITTI and nuScenes benchmarks demonstrate the effectiveness of our method, especially for the hard setting objects with fewer points.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    S²CNet: Semantic and Structure Completion Network for 3D Object Detection


    Beteiligte:
    Shi, Chao (Autor:in) / Zhang, Chongyang (Autor:in) / Luo, Yan (Autor:in) / Qian, Zefeng (Autor:in) / Zhao, Muming (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.11.2024


    Format / Umfang :

    14273748 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Object image completion

    SANJA FIDLER / DAVID ACUNA MARRERO / SEUNG WOOK KIM et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Instance-Aware Monocular 3D Semantic Scene Completion

    Xiao, Haihong / Xu, Hongbin / Kang, Wenxiong et al. | IEEE | 2024


    PASFLN: Positional Association and Semantic Fusion Learning Network for Traffic Object Detection

    Yin, Yunfei / Kou, Tingli / Ochieng, Nyambega D. et al. | IEEE | 2023


    SPARSE VOXEL TRANSFORMER FOR CAMERA-BASED 3D SEMANTIC SCENE COMPLETION

    LI YIMING / YU ZHIDING / CHOY CHRISTOPHER B et al. | Europäisches Patentamt | 2024

    Freier Zugriff