Noisy-Residual Continuous Diffusion Models for Real Image Denoising

The generation paradigm of diffusion model (DM) inspires numerous works to approach the image denoising problem iteratively. However, DM-based image denoising methods typically require long serial sampling chains, resulting in substantial sampling time and computation. To address this issue, we propose a Noisy-Residual Continuous Diffusion Model (RCDM). It constructs a path between clean and noisy images by shifting their noisy residual during forward process, which significantly shortens diffusion distance. To approximate the path, Noisy Residual Tracer Network (NRTNet) is adopted to estimate the derivative of each point along the path. For further acceleration, clean images are iteratively sampled from noisy images in the reverse process, where the sampling intervals are learnable and skippable. Moreover, we devise a two-stage training strategy to minimize the curvature of the learned path. Experimental results demonstrate that the proposed method achieves superior performance with fewer sampling steps in real image denoising.

I. Introduction

Image denoising aims to recover clean images from distorted ones corrupted by different types of noise, which is ill-posed and a challenging task. Image denoising holds practical significance in various real-life scenarios, spanning from medical imaging to surveillance systems, which is attributed to the enhancement of image representation and the improved accuracy of visual analysis [1]. Consequently, image denoising attracts considerable attention due to its diverse applications and the demand for high-quality images.