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
  • [1] TG-Pose: Delving Into Topology and Geometry for Category-Level Object Pose Estimation
    Zhan, Yue
    Wang, Xin
    Nie, Lang
    Zhao, Yang
    Yang, Tangwen
    Ruan, Qiuqi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 9749 - 9762
  • [2] Category-Level Articulated Object Pose Estimation
    Li, Xiaolong
    Wang, He
    Yi, Li
    Guibas, Leonidas
    Abbott, A. Lynn
    Song, Shuran
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 3703 - 3712
  • [3] GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence
    Wang, Pengyuan
    Ikeda, Takuya
    Lee, Robert
    Nishiwaki, Koichi
    COMPUTER VISION - ECCV 2024, PT XXVII, 2025, 15085 : 108 - 126
  • [4] Category-Level Object Pose Estimation with Statistic Attention
    Jiang, Changhong
    Mu, Xiaoqiao
    Zhang, Bingbing
    Liang, Chao
    Xie, Mujun
    SENSORS, 2024, 24 (16)
  • [5] GPT-COPE: A Graph-Guided Point Transformer for Category-Level Object Pose Estimation
    Zou, Lu
    Huang, Zhangjin
    Gu, Naijie
    Wang, Guoping
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (04) : 2385 - 2398
  • [6] GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
    Zhang, Jiyao
    Wu, Mingdong
    Dong, Hao
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [7] A Visual Navigation Perspective for Category-Level Object Pose Estimation
    Guo, Jiaxin
    Zhong, Fangxun
    Xiong, Rong
    Liu, Yunhui
    Wang, Yue
    Liao, Yiyi
    COMPUTER VISION - ECCV 2022, PT VI, 2022, 13666 : 123 - 141
  • [8] iCaps: Iterative Category-Level Object Pose and Shape Estimation
    Deng, Xinke
    Geng, Junyi
    Bretl, Timothy
    Xiang, Yu
    Fox, Dieter
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02): : 1784 - 1791
  • [9] Zero-Shot Category-Level Object Pose Estimation
    Goodwin, Walter
    Vaze, Sagar
    Havoutis, Ioannis
    Posner, Ingmar
    COMPUTER VISION, ECCV 2022, PT XXXIX, 2022, 13699 : 516 - 532
  • [10] Category-Level Metric Scale Object Shape and Pose Estimation
    Lee, Taeyeop
    Lee, Byeong-Uk
    Kim, Myungchul
    Kweon, I. S.
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04) : 8575 - 8582