Addressing accuracy limitations and 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 Langevin dynamics but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.

翻译：从单张RGB图像进行6D物体姿态估计时，精度限制与姿态歧义性（尤其由物体对称性或遮挡引起）是亟待解决的关键难题。为此，我们提出一种应用于$SE(3)$群的新型分数扩散方法，首次将扩散模型应用于图像域中的$SE(3)$群，并专门针对姿态估计任务进行设计。大量实验表明，该方法能有效处理姿态歧义、缓解透视引起的歧义性，并验证了我们提出的$SE(3)$群替代Stein分数公式的鲁棒性。该公式不仅改进了Langevin动力学的收敛性，还提升了计算效率。由此，我们开创了一种具有前景的6D物体姿态估计策略。