EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

RNNPose: 6-DoF Object Pose Estimation via Recurrent Correspondence Field Estimation and Pose Optimization

Yan Xu, Kwan-Yee Lin, Guofeng Zhang, Xiaogang Wang, Hongsheng Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-07 · 46 (7) · 4669-4683

DOI: 10.1109/tpami.2024.3360181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-07. Verfasst von Yan Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key R&D Program of China Project, Centre for Perceptual and Interactive Intelligence (CPII) Ltd., Innovation and Technology Commission (ITC)'s InnoHK.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

6-DoF object pose estimation from a monocular image is a challenging problem, where a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework, dubbed RNNPose, based on a recurrent neural network (RNN) for object pose refinement, which is robust to erroneous initial poses and occlusions. During the recurrent iterations, object pose refinement is formulated as a non-linear least squares problem based on the estimated correspondence field (between a rendered image and the observed image). The problem is then solved by a differentiable Levenberg-Marquardt (LM) algorithm enabling end-to-end training. The correspondence field estimation and pose refinement are conducted alternately in each iteration to improve the object poses. Furthermore, to improve the robustness against occlusion, we introduce a consistency-check mechanism based on the learned descriptors of the 3D model and observed 2D images, which downweights the unreliable correspondences during pose optimization. We evaluate RNNPose on several public datasets, including LINEMOD, Occlusion-LINEMOD, YCB-Video and TLESS. We demonstrate state-of-the-art performance and strong robustness against severe clutter and occlusion in the scenes. Extensive experiments validate the effectiveness of our proposed method. Besides, the extended system based on RNNPose successfully generalizes to multi-instance scenarios and achieves top-tier performance on the TLESS dataset.

Förderung

  • National Key R&D Program of China Project
  • Centre for Perceptual and Interactive Intelligence (CPII) Ltd.
  • Innovation and Technology Commission (ITC)'s InnoHK
  • General Research Fund of Hong Kong RGC Project
  • PI of CPII
  • InnoHK

Zitieren

APA

Xu, Y., Lin, K. Y., Zhang, G., Wang, X., & Li, H. (2024). RNNPose: 6-DoF Object Pose Estimation via Recurrent Correspondence Field Estimation and Pose Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7), 4669-4683. https://doi.org/10.1109/tpami.2024.3360181

Vancouver

Xu Y, Lin KY, Zhang G, Wang X, Li H. RNNPose: 6-DoF Object Pose Estimation via Recurrent Correspondence Field Estimation and Pose Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(7):4669-4683. doi:10.1109/tpami.2024.3360181

BibTeX
@article{Xu2024,
  author = {Xu, Yan and Lin, Kwan-Yee and Zhang, Guofeng and Wang, Xiaogang and Li, Hongsheng},
  title = {RNNPose: 6-DoF Object Pose Estimation via Recurrent Correspondence Field Estimation and Pose Optimization},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {7},
  pages = {4669--4683},
  doi = {10.1109/tpami.2024.3360181}
}
Kostenlos starten →