Existing data augmentation approaches on LiDAR point cloud are mostly developed on rigid transformation, such as rotation, flipping, or copy-based and mix-based methods, lacking the capability to generate diverse samples that depict smooth deformations in real-world scenarios. In response, we propose a novel and effective LiDAR point cloud augmentation approach with smooth deformations that can enrich the diversity of training data while keeping the topology of instances and scenes simultaneously. The whole augmentation pipeline can be separated into two different parts: scene augmentation and instance augmentation. To simplify the selection of deformation functions and ensure control over augmentation outcomes, we propose three effective strategies: residual mapping, space decoupling, and function periodization, respectively. We also propose an effective prior-based location sampling algorithm to paste instances on a more reasonable area in the scenes. Extensive experiments on both the SemanticKITTI and nuScenes challenging datasets demonstrate the effectiveness of our proposed approach across various baselines.


    Access

    Download


    Export, share and cite



    Title :

    Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation


    Contributors:
    Qiu, Shoumeng (author) / Chen, Jie (author) / Lai, Chenghang (author) / Lu, Hong (author) / Xue, Xiangyang (author) / Pu, Jian (author)

    Published in:

    Publication date :

    2024-02-01


    Size :

    6270540 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Fast Semantic Segmentation of 3D Lidar Point Cloud Based on Random Forest Method

    Jiang, Songdi / Guo, Wei / Fan, Yuzhi et al. | Springer Verlag | 2022


    Fast Semantic Segmentation of 3D Lidar Point Cloud Based on Random Forest Method

    Jiang, Songdi / Guo, Wei / Fan, Yuzhi et al. | TIBKAT | 2022


    Vehicle Detection and Localization using 3D LIDAR Point Cloud and Image Semantic Segmentation

    Barea, Rafael / Perez, Carlos / Bergasa, Luis M. et al. | IEEE | 2018


    IMPROVING LIDAR POINT CLOUD SEGMENTATION USING BOX PREDICTION

    ZHOU LUBING / MENG XIAOLI / SHETTI KARAN RAJENDRA | European Patent Office | 2022

    Free access

    CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation

    Zhao, Guoyang / Ma, Fulong / Qi, Weiqing et al. | IEEE | 2025