The acquisition of both local and global features from irregular point clouds is crucial for 3D object detection (3DOD). Current mainstream 3D detectors neglect significant local features during pooling operations or disregard many global features of the overall scene context. This paper proposes new techniques for simultaneously learning local-global features of scene point clouds to enhance 3DOD. Specifically, we propose an efficient 3DOD network in indoor point clouds, named SimLOG, which utilizes simultaneous local-global feature learning. SimLOG has two main contributions: a Dynamic Points Interaction (DPI) module to recover local features lost during pooling, and a Global Context Aggregation(GCA) module to aggregate multi-scale features from various layers of the encoder to improve scene context awareness. Unlike traditional local-global feature learning methods, our DPI and GCA modules are integrated into a single feature learning module, making it easily detachable and able to be incorporated into existing 3DOD networks to enhance their performance. SimLOG demonstrates superior performance over twenty competitors in terms of detection accuracy and robustness on both the SUN RGB-D and ScanNet V2 datasets. Specifically, SimLOG boosts the baseline VoteNet by 8.1% of mAP@0.25 on ScanNet V2 and by 3.9% of mAP@0.25 on SUN RGB-D. Code is publicly available at https://github.com/chenbaian-cs/SimLOG.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    SimLOG: Simultaneous Local-Global Feature Learning for 3D Object Detection in Indoor Point Clouds


    Contributors:
    Wei, Mingqiang (author) / Chen, Baian (author) / Nan, Liangliang (author) / Xie, Haoran (author) / Gu, Lipeng (author) / Lu, Dening (author) / Lee Wang, Fu (author) / Li, Qing (author)

    Published in:

    Publication date :

    2024-12-01


    Size :

    7263566 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds

    Tian, Yonglin / Huang, Lichao / Yu, Hui et al. | IEEE | 2022


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

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


    Top-down object detection from LiDAR point clouds

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | European Patent Office | 2024

    Free access

    TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | European Patent Office | 2024

    Free access

    TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | European Patent Office | 2021

    Free access