GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

被引:65
|
作者
Di, Yan [1 ]
Zhang, Ruida [2 ]
Lou, Zhiqiang [2 ]
Manhardt, Fabian [3 ]
Ji, Xiangyang [2 ]
Navab, Nassir [1 ]
Tombari, Federico [1 ]
机构
[1] Tech Univ Munich, Munich, Germany
[2] Tsinghua Univ, Beijing, Peoples R China
[3] Google, Mountain View, CA 94043 USA
关键词
D O I
10.1109/CVPR52688.2022.00666
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
While 6D object pose estimation has recently made a huge leap forward, most methods can still only handle a single or a handful of different objects, which limits their applications. To circumvent this problem, category-level object pose estimation has recently been revamped, which aims at predicting the 6D pose as well as the 3D metric size for previously unseen instances from a given set of object classes. This is, however, a much more challenging task due to severe intra-class shape variations. To address this issue, we propose GPV-Pose, a novel framework for robust category-level pose estimation, harnessing geometric insights to enhance the learning of category-level pose-sensitive features. First, we introduce a decoupled confidence-driven rotation representation, which allows geometry-aware recovery of the associated rotation matrix. Second, we propose a novel geometry-guided point-wise voting paradigm for robust retrieval of the 3D object bounding box. Finally, leveraging these different output streams, we can enforce several geometric consistency terms, further increasing performance, especially for non-symmetric categories. GPV-Pose produces superior results to state-of-the-art competitors on common public benchmarks, whilst almost achieving real-time inference speed at 20 FPS.
引用
收藏
页码:6771 / 6781
页数:11
相关论文
共 50 条
  • [21] SD-Pose: Structural Discrepancy Aware Category-Level 6D Object Pose Estimation
    Li, Guowei
    Zhu, Dongchen
    Zhang, Guanghui
    Shi, Wenjun
    Zhang, Tianyu
    Zhang, Xiaolin
    Li, Jiamao
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 5674 - 5683
  • [22] Best Next-Viewpoint Recommendation by Selecting Minimum Pose Ambiguity for Category-Level Object Pose Estimation
    Hashim N.M.Z.
    Kawanishi Y.
    Deguchi D.
    Ide I.
    Amma A.
    Kobori N.
    Murase H.
    Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, 2021, 87 (05): : 440 - 446
  • [23] Category-level pipe pose and size estimation via geometry-aware adaptive curvature convolution
    Hu, Jia
    Liu, Jianhua
    Liu, Shaoli
    Wang, Lifeng
    APPLIED SOFT COMPUTING, 2025, 174
  • [24] KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation
    Meng, Qiwei
    Gu, Jason
    Zhu, Shiqiang
    Liao, Jianfeng
    Jin, Tianlei
    Guo, Fangtai
    Wang, Wen
    Song, Wei
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, : 6102 - 6108
  • [25] SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation
    Chen, Kai
    Dou, Qi
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 2753 - 2762
  • [26] UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
    Lee, Taeyeop
    Lee, Byeong-Uk
    Shin, Inkyu
    Choe, Jaesung
    Shin, Ukcheol
    Kweon, In So
    Yoon, Kuk-Jin
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 14871 - 14880
  • [27] Optimal Pose and Shape Estimation for Category-level 3D Object Perception
    Shi, Jingnan
    Yang, Heng
    Carlone, Luca
    ROBOTICS: SCIENCE AND SYSTEM XVII, 2021,
  • [28] RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation
    Zhang, Ruida
    Di, Yan
    Lou, Zhiqiang
    Manhardi, Fabian
    Tombari, Federico
    Ji, Xiangyang
    COMPUTER VISION - ECCV 2022, PT I, 2022, 13661 : 655 - 672
  • [29] VoCAPTER: Voting-based Pose Tracking for Category-level Articulated Object via Inter-frame Priors
    Zhang, Li
    Han, Zean
    Zhong, Yan
    Yu, Qiaojun
    Wu, Xingyu
    Wang, Xue
    Wang, Rujing
    MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia, : 8942 - 8951
  • [30] SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation
    Zhang, Ruida
    Di, Yan
    Manhardt, Fabian
    Tombari, Federico
    Ji, Xiangyang
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 7452 - 7459