LGJul 14, 2025

Parallel Sampling of Diffusion Models on $SO(3)$

arXiv:2507.10347v11 citationsh-index: 62025 19th International Conference on Machine Vision and Applications (MVA)
Originality Incremental advance
AI Analysis

This work addresses latency reduction for pose ambiguity problems in robotics or computer vision, but it is incremental as it builds on existing diffusion methods.

The paper tackles the slow sequential denoising in diffusion models on the SO(3) manifold by adapting Picard iteration, achieving a speed-up of up to 4.9× without degrading task reward.

In this paper, we design an algorithm to accelerate the diffusion process on the $SO(3)$ manifold. The inherently sequential nature of diffusion models necessitates substantial time for denoising perturbed data. To overcome this limitation, we proposed to adapt the numerical Picard iteration for the $SO(3)$ space. We demonstrate our algorithm on an existing method that employs diffusion models to address the pose ambiguity problem. Moreover, we show that this acceleration advantage occurs without any measurable degradation in task reward. The experiments reveal that our algorithm achieves a speed-up of up to 4.9$\times$, significantly reducing the latency for generating a single sample.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes