Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

Tsu-Ching Hsiao   Hao-Wei Chen   Hsuan-Kung Yang   Chun-Yi Lee
Elsa Lab, National Tsing Hua University
CVPR 2024
Paper Code arXiv
liepose-diffusion

Visualization of the denoising process through time index of our score-based diffusion method on SE(3) for 6DoF pose estimation.

Abstract

Addressing pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the SE(3) group, marking the first application of diffusion models to SE(3) within the image domain, specifically tailored for pose estimation tasks. Extensive evaluations demonstrate the method's efficacy in handling pose ambiguity, mitigating perspective-induced ambiguity, and showcasing the robustness of our surrogate Stein score formulation on SE(3). This formulation not only improves the convergence of denoising process but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.

Visualization of the estimated probability distribution on SE(3) for the T-LESS dataset.

Video Presentation

SYMSOL-T Demos

Poster

BibTeX


      @inproceedings{hsiao2024confronting,
          title={Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)},
          author={Hsiao, Tsu-Ching and Chen, Hao-Wei and Yang, Hsuan-Kung and Lee, Chun-Yi},
          booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
          pages={352--362},
          year={2024}
      }