ending2015a / liepose-diffusion

[CVPR 2024] Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

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

CVPR 2024

Tsu-Ching Hsiao  Hao-Wei Chen  Hsuan-Kung Yang  Chun-Yi Lee 
Elsa Lab, National Tsing Hua University

| arXiv |

Official implementation in JAX.

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.

Code

TBA

Videos

output.mp4

output.mp4

output.mp4

output.mp4

output.mp4

Cite

TBA

liepose-diffusion's Issues

Some questions

This is an outstanding paper.
How can I be successful just like you?😁😁

If you have any tips, please let me know.