NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration

TL;DR

NFCDS introduces a spectral filtering approach in diffusion sampling that balances image fidelity and perceptual quality by controlling noise frequency components, enhancing image restoration without extra training.

Contribution

The paper presents NFCDS, a plug-and-play spectral modulation mechanism that improves diffusion-based image restoration by controlling noise frequency during sampling.

Findings

Enhances image fidelity while maintaining perceptual quality.

Integrates seamlessly into existing diffusion frameworks.

Achieves fast convergence without additional training.

Abstract

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.