Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

被引:1
|
作者
Chen, Yongwei [1 ,2 ]
Wang, Zihao [1 ]
Zou, Longkun [1 ]
Chen, Ke [1 ,3 ]
Jia, Kui [1 ,3 ]
机构
[1] South China Univ Technol, Guangzhou, Peoples R China
[2] DexForce Co Ltd, Shenzhen, Peoples R China
[3] Peng Cheng Lab, Shenzhen, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
D O I
10.1007/978-3-031-19827-4_42
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. However, learning from synthetic data may not generalize to practical scenarios, where point clouds are typically incomplete, non-uniformly distributed, and noisy. Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured. To this end, we propose an integrated scheme consisting of physically realistic synthesis of object point clouds via rendering stereo images via projection of speckle patterns onto CAD models and a novel quasi-balanced self-training designed for more balanced data distribution by sparsity-driven selection of pseudo labeled samples for long tailed classes. Experiment results can verify the effectiveness of our method as well as both of its modules for unsupervised domain adaptation on point cloud classification, achieving the state-of-the-art performance. Source codes and the SpeckleNet synthetic dataset are available at https://github.com/Gorilla-Lab-SCUT/QS3.
引用
收藏
页码:728 / 745
页数:18
相关论文
共 3 条
  • [1] Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds
    Zou, Longkun
    Tang, Hui
    Chen, Ke
    Jia, Kui
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 6383 - 6392
  • [2] Domain Adaptive LiDAR Point Cloud Segmentation via Density-Aware Self-Training
    Xiao, Aoran
    Huang, Jiaxing
    Liu, Kangcheng
    Guan, Dayan
    Zhang, Xiaoqin
    Lu, Shijian
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024,
  • [3] Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
    Zhang, Yichen
    Lin, Jiehong
    Chen, Ke
    Xu, Zelin
    Wang, Yaowei
    Jia, Kui
    [J]. PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 1740 - 1748