NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration
This addresses the problem of reduced data fidelity in image restoration for users of diffusion-based methods, offering an incremental improvement as a plug-and-play module.
The paper tackled the trade-off between data fidelity and perceptual quality in diffusion sampling-based Plug-and-Play methods for image restoration by proposing NFCDS, a noise frequency-controlled diffusion sampling strategy that uses a Fourier-domain filter to suppress low-frequency noise, resulting in improved fidelity-perception balance across zero-shot tasks without additional training.
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.