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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Beteiligte:
    Yuan, Zhimin (Autor:in) / Wen, Chenglu (Autor:in) / Cheng, Ming (Autor:in) / Su, Yanfei (Autor:in) / Liu, Weiquan (Autor:in) / Yu, Shangshu (Autor:in) / Wang, Cheng (Autor:in)


    Erscheinungsdatum :

    01.02.2023


    Format / Umfang :

    3760520 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    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, Jan / Langer, D. / Muller-Bessler, B. et al. | IEEE | 2011


    Efficient Segmentation of 3D LIDAR Point Clouds Handling Partial Occlusion

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