Effective and efficient 3D semantic segmentation from large-scale LiDAR point cloud is a fundamental problem in the field of autonomous driving. In this paper, we present Transformer-Range-View Network (TransRVNet), a novel and powerful projection-based CNN-Transformer architecture to infer point-wise semantics. First, a Multi Residual Channel Interaction Attention Module (MRCIAM) is introduced to capture channel-level multi-scale feature and model intra-channel, inter-channel correlations based on attention mechanism. Then, in the encoder stage, we use a well-designed Residual Context Aggregation Module (RCAM), including a residual dilated convolution structure and a context aggregation module, to fuse information from different receptive fields while reducing the impact of missing points. Finally, a Balanced Non-square-Transformer Module (BNTM) is employed as fundamental component of decoder to achieve locally feature dependencies for more discriminative feature learning by introducing the non-square shifted window strategy. Extensive qualitative and quantitative experiments conducted on challenging SemanticKITTI and SemanticPOSS benchmarks have verified the effectiveness of our proposed technique. Our TransRVNet presents superior performance over most existing state-of-the-art approaches. The source code and trained model are available at https://github.com/huixiancheng/TransRVNet.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    TransRVNet: LiDAR Semantic Segmentation With Transformer


    Beteiligte:
    Cheng, Hui-Xian (Autor:in) / Han, Xian-Feng (Autor:in) / Xiao, Guo-Qiang (Autor:in)


    Erscheinungsdatum :

    01.06.2023


    Format / Umfang :

    3751706 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Lidar Mapping Optimization Based on Lightweight Semantic Segmentation

    Zhao, Zhihao / Zhang, Wenquan / Gu, Jianfeng et al. | IEEE | 2019


    Supervised Learning for Semantic Segmentation of 3D LiDAR Data

    Mei, Jilin / Chen, Jiayu / Yao, Wen et al. | IEEE | 2019


    Camera-Based Semantic Enhanced Vehicle Segmentation for Planar LIDAR

    Fu, Chen / Hu, Peiyun / Dong, Chiyu et al. | IEEE | 2018


    HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation

    Chen, Siyu / Han, Ting / Zhang, Changshe et al. | IEEE | 2025


    TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation

    Liu, Ruiping / Yang, Kailun / Roitberg, Alina et al. | IEEE | 2024