Real-World Denoising via Diffusion Model

TL;DR

This paper introduces a novel diffusion model with linear interpolation for real-world image denoising, demonstrating competitive performance with state-of-the-art methods using simple CNN architectures.

Contribution

The paper proposes a new diffusion process with linear interpolation and two sampling algorithms tailored for real-world image denoising, expanding diffusion models' application scope.

Findings

Achieves comparable results to Transformer-based methods.

Performs well on real-world denoising benchmarks.

Uses simple CNNs like Unet for effective denoising.

Abstract

Real-world image denoising is an extremely important image processing problem, which aims to recover clean images from noisy images captured in natural environments. In recent years, diffusion models have achieved very promising results in the field of image generation, outperforming previous generation models. However, it has not been widely used in the field of image denoising because it is difficult to control the appropriate position of the added noise. Inspired by diffusion models, this paper proposes a novel general denoising diffusion model that can be used for real-world image denoising. We introduce a diffusion process with linear interpolation, and the intermediate noisy image is interpolated from the original clean image and the corresponding real-world noisy image, so that this diffusion model can handle the level of added noise. In particular, we also introduce two sampling algorithms for this diffusion model. The first one is a simple sampling procedure defined according to the diffusion process, and the second one targets the problem of the first one and makes a number of improvements. Our experimental results show that our proposed method with a simple CNNs Unet achieves comparable results compared to the Transformer architecture. Both quantitative and qualitative evaluations on real-world denoising benchmarks show that the proposed general diffusion model performs almost as well as against the state-of-the-art methods.