DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

被引:6
|
作者
Wen, Yilin [1 ]
Li, Xiangyu [2 ]
Pan, Hao [3 ]
Yang, Lei [1 ,4 ]
Wang, Zheng [5 ]
Komura, Taku [1 ]
Wang, Wenping [6 ]
机构
[1] Univ Hong Kong, Hong Kong, Peoples R China
[2] Brown Univ, Providence, RI 02912 USA
[3] Microsoft Res Asia, Beijing, Peoples R China
[4] Ctr Garment Prod Ltd, Hong Kong, Peoples R China
[5] SUSTech, Shenzhen, Peoples R China
[6] Texas A&M Univ, College Stn, TX USA
来源
关键词
6D pose estimation; Scalability; Disentanglement; Symmetry ambiguity; Re-entanglement; Sim-to-real; REPRESENTATION;
D O I
10.1007/978-3-031-20077-9_24
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects. Building on a well-known auto-encoding framework to cope with object symmetry and the lack of labeled training data, we achieve scalability by disentangling the latent representation of auto-encoder into shape and pose sub-spaces. The latent shape space models the similarity of different objects through contrastive metric learning, and the latent pose code is compared with canonical rotations for rotation retrieval. Because different object symmetries induce inconsistent latent pose spaces, we re-entangle the shape representation with canonical rotations to generate shape-dependent pose codebooks for rotation retrieval. We show state-of-the-art performance on two benchmarks containing textureless CAD objects without category and daily objects with categories respectively, and further demonstrate improved scalability by extending to a more challenging setting of daily objects across categories.
引用
收藏
页码:404 / 421
页数:18
相关论文
共 50 条
  • [31] 6D Pose Estimation for Subsea Intervention in Turbid Waters
    Mohammed, Ahmed
    Kvam, Johannes
    Thielemann, Jens T.
    Haugholt, Karl H.
    Risholm, Petter
    ELECTRONICS, 2021, 10 (19)
  • [32] Confidence-Based 6D Object Pose Estimation
    Huang, Wei-Lun
    Hung, Chun-Yi
    Lin, I-Chen
    IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 : 3025 - 3035
  • [33] Focal segmentation for robust 6D object pose estimation
    Ye, Yuning
    Park, Hanhoon
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (16) : 47563 - 47585
  • [34] DeepIM: Deep Iterative Matching for 6D Pose Estimation
    Li, Yi
    Wang, Gu
    Ji, Xiangyang
    Xiang, Yu
    Fox, Dieter
    COMPUTER VISION - ECCV 2018, PT VI, 2018, 11210 : 695 - 711
  • [35] The 6D Pose Estimation of the Aircraft Using Geometric Property
    Fu, Daoyong
    Han, Songchen
    Liang, Binbin
    Li, Wei
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (07) : 3358 - 3368
  • [36] Generalizable and Accurate 6D Object Pose Estimation Network
    Fu, Shouxu
    Li, Xiaoning
    Yu, Xiangdong
    Cao, Lu
    Li, Xingxing
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT III, 2024, 14427 : 312 - 324
  • [37] Segmentation-driven 6D Object Pose Estimation
    Hu, Yinlin
    Hugonot, Joachim
    Fua, Pascal
    Salzmann, Mathieu
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 3380 - 3389
  • [38] 6D Object Pose Estimation for Robot Programming by Demonstration
    Ghahramani, Mohammad
    Vakanski, Aleksandar
    Janabi-Sharifi, Farrokh
    PROGRESS IN OPTOMECHATRONIC TECHNOLOGIES, 2019, 233 : 93 - 101
  • [39] RobotP: A Benchmark Dataset for 6D Object Pose Estimation
    Yuan, Honglin
    Hoogenkamp, Tim
    Veltkamp, Remco C.
    SENSORS, 2021, 21 (04) : 1 - 26
  • [40] 6D Object Pose Estimation Based on the Attention Mechanism
    Zhou, Guanyu
    INTERNATIONAL CONFERENCE ON ALGORITHMS, HIGH PERFORMANCE COMPUTING, AND ARTIFICIAL INTELLIGENCE (AHPCAI 2021), 2021, 12156