English

FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise

Image and Video Processing 2025-02-20 v2 Graphics

Abstract

Text-driven video generation has advanced significantly due to developments in diffusion models. Beyond the training and sampling phases, recent studies have investigated noise priors of diffusion models, as improved noise priors yield better generation results. One recent approach employs the Fourier transform to manipulate noise, marking the initial exploration of frequency operations in this context. However, it often generates videos that lack motion dynamics and imaging details. In this work, we provide a comprehensive theoretical analysis of the variance decay issue present in existing methods, contributing to the loss of details and motion dynamics. Recognizing the critical impact of noise distribution on generation quality, we introduce FreqPrior, a novel noise initialization strategy that refines noise in the frequency domain. Our method features a novel filtering technique designed to address different frequency signals while maintaining the noise prior distribution that closely approximates a standard Gaussian distribution. Additionally, we propose a partial sampling process by perturbing the latent at an intermediate timestep during finding the noise prior, significantly reducing inference time without compromising quality. Extensive experiments on VBench demonstrate that our method achieves the highest scores in both quality and semantic assessments, resulting in the best overall total score. These results highlight the superiority of our proposed noise prior.

Keywords

Cite

@article{arxiv.2502.03496,
  title  = {FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise},
  author = {Yunlong Yuan and Yuanfan Guo and Chunwei Wang and Wei Zhang and Hang Xu and Li Zhang},
  journal= {arXiv preprint arXiv:2502.03496},
  year   = {2025}
}

Comments

ICLR 2025

R2 v1 2026-06-28T21:33:55.617Z