Unsupervised domain adaptation (UDA) is a low-cost way to deal with the lack of annotations in a new domain. For outdoor point clouds in urban transportation scenes, the mismatch of sampling patterns and the transferability difference between classes make cross-domain segmentation extremely difficult. To overcome these challenges, we propose a category-level adversarial framework. Firstly, we propose a multi-scale domain conditioned block that facilitates to extract the critical low-level domain-dependent knowledge and reduce the domain gap caused by distinct LiDAR sampling patterns. Secondly, we make full use of multiple representation forms (i.e., point-based sets and voxel-based cells) and utilize the prediction consistency between the two forms to measure how well each point is semantically aligned. The model then focuses on the poorly-aligned points without affecting the well-aligned points. Experimental results on three autonomous driving point cloud datasets show that the proposed method outperforms existing methods by a large margin, especially on the low-beam to high-beam cross-domain segmentation task.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Category-Level Adversaries for Outdoor LiDAR Point Clouds Cross-Domain Semantic Segmentation


    Contributors:
    Yuan, Zhimin (author) / Wen, Chenglu (author) / Cheng, Ming (author) / Su, Yanfei (author) / Liu, Weiquan (author) / Yu, Shangshu (author) / Wang, Cheng (author)


    Publication date :

    2023-02-01


    Size :

    3760520 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study

    Triess, Larissa T. / Peter, David / Rist, Christoph B. et al. | IEEE | 2020


    Axial Attention Inside a U-Net for Semantic Segmentation of 3D Sparse LiDAR Point Clouds

    Yin, Tang-Kai / Wu, Liang-Yue / Hong, Tzung-Pei | IEEE | 2022


    SCSSnet: Learning Spatially-Conditioned Scene Segmentation on LiDAR Point Clouds

    Rist, Christoph B. / Schmidt, David / Enzweiler, Markus et al. | IEEE | 2020


    Efficient Segmentation of 3D LIDAR Point Clouds Handling Partial Occlusion

    Aue, J. / Langer, D. / Mueller-Bessler, B. et al. | British Library Conference Proceedings | 2011


    Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information

    Certad, Novel / Morales-Alvarez, Walter / Olaverri-Monreal, Cristina | IEEE | 2022