Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

被引:0
|
作者
Hai, Yang [1 ]
Song, Rui [1 ]
Li, Jiaojiao [1 ]
Ferstl, David [2 ]
Hu, Yinlin [2 ]
机构
[1] Xidian Univ, State Key Lab ISN, Xian, Shaanxi, Peoples R China
[2] MagicLeap, Plantation, FL USA
关键词
D O I
10.1109/ICCV51070.2023.01294
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range. In this paper, we propose a 6D object pose estimation method that can be trained with pure RGB images without any auxiliary information. We first obtain a rough pose initialization from networks trained on synthetic images rendered from the target's 3D mesh. Then, we introduce a refinement strategy leveraging the geometry constraint in synthetic-to-real image pairs from multiple different views. We formulate this geometry constraint as pixel-level flow consistency between the training images with dynamically generated pseudo labels. We evaluate our method on three challenging datasets and demonstrate that it outperforms state-of-the-art self-supervised methods significantly, with neither 2D annotations nor additional depth images.
引用
收藏
页码:14029 / 14039
页数:11
相关论文
共 50 条
  • [1] Self-Supervised Category-Level 6D Object Pose Estimation With Optical Flow Consistency
    Zaccaria, Michela
    Manhardt, Fabian
    Di, Yan
    Tombari, Federico
    Aleotti, Jacopo
    Giorgini, Mikhail
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (05) : 2510 - 2517
  • [2] Self-supervised 6D Object Pose Estimation for Robot Manipulation
    Deng, Xinke
    Xiang, Yu
    Mousavian, Arsalan
    Eppner, Clemens
    Bretl, Timothy
    Fox, Dieter
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 3665 - 3671
  • [3] Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
    Sock, Juil
    Garcia-Hernando, Guillermo
    Armagan, Anil
    Kim, Tae-Kyun
    [J]. 2020 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2020), 2020, : 291 - 300
  • [4] TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation
    Chen, Hanzhi
    Manhardt, Fabian
    Navab, Nassir
    Busam, Benjamin
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 4841 - 4852
  • [5] Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
    Wang, Gu
    Manhardt, Fabian
    Liu, Xingyu
    Ji, Xiangyang
    Tombari, Federico
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1788 - 1803
  • [6] Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation
    Peng, Wanli
    Yan, Jianhang
    Wen, Hongtao
    Sun, Yi
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 2082 - 2090
  • [7] Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks
    Lin, Jiehong
    Wei, Zewei
    Ding, Changxing
    Jia, Kui
    [J]. COMPUTER VISION, ECCV 2022, PT IX, 2022, 13669 : 19 - 34
  • [8] On Evaluation of 6D Object Pose Estimation
    Hodan, Tomas
    Matas, Jiri
    Obdrzalek, Stephan
    [J]. COMPUTER VISION - ECCV 2016 WORKSHOPS, PT III, 2016, 9915 : 606 - 619
  • [9] GeoPose: Dense Reconstruction Guided 6D Object Pose Estimation With Geometric Consistency
    Wang, Deming
    Zhou, Guangliang
    Yan, Yi
    Chen, Huiyi
    Chen, Qijun
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 : 4394 - 4408
  • [10] BOP: Benchmark for 6D Object Pose Estimation
    Hodan, Tomas
    Michel, Frank
    Brachmann, Eric
    Kehl, Wadim
    Buch, Anders Glent
    Kraft, Dirk
    Drost, Bertram
    Vidal, Joel
    Ihrke, Stephan
    Zabulis, Xenophon
    Sahin, Caner
    Manhardt, Fabian
    Tombari, Federico
    Kim, Tae-Kyun
    Matas, Jiri
    Rother, Carsten
    [J]. COMPUTER VISION - ECCV 2018, PT X, 2018, 11214 : 19 - 35