Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

被引:5
作者
Dang, Zheng [1 ]
Wang, Lizhou [2 ]
Guo, Yu [2 ]
Salzmann, Mathieu [1 ,3 ]
机构
[1] Ecole Polytech Fed Lausanne, CVLab, Lausanne, Switzerland
[2] Xi An Jiao Tong Univ, Xian, Shaanxi, Peoples R China
[3] Clearspace, Renens, Switzerland
来源
COMPUTER VISION - ECCV 2022, PT I | 2022年 / 13661卷
关键词
6D object pose estimation; Point cloud registration;
D O I
10.1007/978-3-031-19769-7_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in the presence of real-world data. We thus analyze the causes of these failures, which we trace back to the difference between the feature distributions of the source and target point clouds, and the sensitivity of the widely-used SVD-based loss function to the range of rotation between the two point clouds. We address the first challenge by introducing a new normalization strategy, Match Normalization, and the second via the use of a loss function based on the negative log likelihood of point correspondences. Our two contributions are general and can be applied to many existing learning-based 3D object registration frameworks, which we illustrate by implementing them in two of them, DCP and IDAM. Our experiments on the real-scene TUD-L [26], LINEMOD [23] and Occluded-LINEMOD [T] datasets evidence the benefits of our strategies. They allow for the first time learning-based 3D object registration methods to achieve meaningful results on real-world data. We therefore expect them to be key to the future development of point cloud registration methods.
引用
收藏
页码:19 / 37
页数:19
相关论文
共 76 条
  • [1] Agamennoni G, 2016, 2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), P4092, DOI 10.1109/IROS.2016.7759602
  • [2] 4-points congruent sets for robust pairwise surface registration
    Aiger, Dror
    Mitra, Niloy J.
    Cohen-Or, Daniel
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2008, 27 (03):
  • [3] Alshahwan N., 2018, LNCS, V1036
  • [4] PointNetLK: Robust & Efficient Point Cloud Registration using PointNet
    Aoki, Yasuhiro
    Goforth, Hunter
    Srivatsan, Rangaprasad Arun
    Lucey, Simon
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 7156 - 7165
  • [5] Point Convolutional Neural Networks by Extension Operators
    Atzmon, Matan
    Maron, Haggai
    Lipman, Yaron
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (04):
  • [6] A METHOD FOR REGISTRATION OF 3-D SHAPES
    BESL, PJ
    MCKAY, ND
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) : 239 - 256
  • [7] Sparse Iterative Closest Point
    Bouaziz, Sofien
    Tagliasacchi, Andrea
    Pauly, Mark
    [J]. COMPUTER GRAPHICS FORUM, 2013, 32 (05) : 113 - 123
  • [8] Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image
    Brachmann, Eric
    Michel, Frank
    Krull, Alexander
    Yang, Michael Ying
    Gumhold, Stefan
    Rother, Carsten
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3364 - 3372
  • [9] Brachmann E, 2014, LECT NOTES COMPUT SC, V8690, P536, DOI 10.1007/978-3-319-10605-2_35
  • [10] Bronstein AM, 2008, LECT NOTES COMPUT SC, V5303, P143, DOI 10.1007/978-3-540-88688-4_11