Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Zhen, Liu, Hongyi, Li, Jianing, Wei, Zhihui
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.21248
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911405684293632
author Wang, Zhen
Liu, Hongyi
Li, Jianing
Wei, Zhihui
author_facet Wang, Zhen
Liu, Hongyi
Li, Jianing
Wei, Zhihui
contents Diffusion sampling-based Plug-and-Play (PnP) methods produce images with high perceptual quality but often suffer from reduced data fidelity, primarily due to the noise introduced during reverse diffusion. To address this trade-off, we propose Noise Frequency-Controlled Diffusion Sampling (NFCDS), a spectral modulation mechanism for reverse diffusion noise. We show that the fidelity-perception conflict can be fundamentally understood through noise frequency: low-frequency components induce blur and degrade fidelity, while high-frequency components drive detail generation. Based on this insight, we design a Fourier-domain filter that progressively suppresses low-frequency noise and preserves high-frequency content. This controlled refinement injects a data-consistency prior directly into sampling, enabling fast convergence to results that are both high-fidelity and perceptually convincing--without additional training. As a PnP module, NFCDS seamlessly integrates into existing diffusion-based restoration frameworks and improves the fidelity-perception balance across diverse zero-shot tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21248
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration
Wang, Zhen
Liu, Hongyi
Li, Jianing
Wei, Zhihui
Computer Vision and Pattern Recognition
Diffusion sampling-based Plug-and-Play (PnP) methods produce images with high perceptual quality but often suffer from reduced data fidelity, primarily due to the noise introduced during reverse diffusion. To address this trade-off, we propose Noise Frequency-Controlled Diffusion Sampling (NFCDS), a spectral modulation mechanism for reverse diffusion noise. We show that the fidelity-perception conflict can be fundamentally understood through noise frequency: low-frequency components induce blur and degrade fidelity, while high-frequency components drive detail generation. Based on this insight, we design a Fourier-domain filter that progressively suppresses low-frequency noise and preserves high-frequency content. This controlled refinement injects a data-consistency prior directly into sampling, enabling fast convergence to results that are both high-fidelity and perceptually convincing--without additional training. As a PnP module, NFCDS seamlessly integrates into existing diffusion-based restoration frameworks and improves the fidelity-perception balance across diverse zero-shot tasks.
title NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.21248