3D point clouds can offer rich geometric content of information for the scenes. How to learn geometric features locally and globally has become a growing concern recently. This paper proposes a novel approach for Point cloud Analysis based on Transformer network, called PAT, which utilizes interactive-attention to capture multi-angle features in irregular point clouds for classification and segmentation. Specifically, the double-coordinate encoder is designed as local filter operations by mining neighborhood information from point coordinates and direction simultaneously in the bi-coordinate system. The proposed PAT for point cloud analysis can interactively perform local and global attention across different feature spaces. Validation was conducted on two public datasets and results show that the proposed PAT achieves good performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    PAT: Point Cloud Analysis with Local Filter Embedding in Transformer


    Contributors:
    Li, Xi (author) / Fan, Siqi (author) / Chen, Yuanyuan (author) / Liu, Yu-Liang (author) / Chen, Shichao (author) / Zhu, Fenghua (author) / Lv, Yisheng (author)


    Publication date :

    2022-10-08


    Size :

    2624066 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    LFT-Net: Local Feature Transformer Network for Point Clouds Analysis

    Gao, Yongbin / Liu, Xuebing / Li, Jun et al. | IEEE | 2023


    Neighbor-based point cloud filter system

    LIU XIANG / GAO DONGCHAO / GAO BIN et al. | European Patent Office | 2023

    Free access

    3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification

    Lu, Dening / Xie, Qian / Gao, Kyle et al. | IEEE | 2022


    NEIGHBOR-BASED POINT CLOUD FILTER SYSTEM

    LIU XIANG / GAO DONGCHAO / GAO BIN et al. | European Patent Office | 2022

    Free access

    SAT3D: Slot Attention Transformer for 3D Point Cloud Semantic Segmentation

    Ibrahim, Muhammad / Akhtar, Naveed / Anwar, Saeed et al. | IEEE | 2023