FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yuan, Yunlong, Guo, Yuanfan, Wang, Chunwei, Zhang, Wei, Xu, Hang, Zhang, Li
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909501574086656
author Yuan, Yunlong
Guo, Yuanfan
Wang, Chunwei
Zhang, Wei
Xu, Hang
Zhang, Li
author_facet Yuan, Yunlong
Guo, Yuanfan
Wang, Chunwei
Zhang, Wei
Xu, Hang
Zhang, Li
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03496
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
Yuan, Yunlong
Guo, Yuanfan
Wang, Chunwei
Zhang, Wei
Xu, Hang
Zhang, Li
Image and Video Processing
Graphics
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.
title FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
topic Image and Video Processing
Graphics
url https://arxiv.org/abs/2502.03496