提出新算法加速SO(3)空间扩散模型采样，提速近5倍。
Parallel Sampling of Diffusion Models on $SO(3)$
- 基于数值皮卡德迭代改进SO(3)上扩散模型的并行采样方法。
- 在不降低任务性能前提下，单样本生成速度提升最高4.9倍。
- 适合需要高效生成三维姿态数据的研究者使用。
本文设计了一种算法，用于加速在SO(3)流形上的扩散过程。扩散模型固有的顺序特性导致去噪扰动数据耗时较长。为克服这一限制，我们提出将数值皮卡德迭代方法适配至SO(3)空间。我们在现有解决姿态歧义问题的扩散模型方法上验证了该算法的有效性。实验表明，该加速优势在不引起任务奖励明显下降的情况下实现。结果表明，本算法使单样本生成延迟显著降低，最高提速达4.9倍。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。