Parallel Sampling of Diffusion Models on SO(3)
Journal
2025 19th International Conference on Machine Vision and Applications (MVA)
Start Page
1-5
Date Issued
2025-07-26
Author(s)
Abstract
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×, significantly reducing the latency for generating a single sample.
Publisher
IEEE
Type
conference paper