Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling

TL;DR

This paper introduces DMID, a novel diffusion model-based approach for image denoising that employs adaptive embedding and ensembling techniques to improve perceptual quality and reduce distortion, achieving state-of-the-art results.

Contribution

It proposes a new diffusion model strategy for image denoising, addressing input and content inconsistencies with adaptive embedding and ensembling methods.

Findings

Achieves state-of-the-art performance on distortion-based metrics

Outperforms existing methods on perception-based metrics

Effective for both Gaussian and real-world image denoising

Abstract

Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion. Recently, the emerging diffusion model has achieved state-of-the-art performance in various tasks and demonstrates great potential for image denoising. However, stimulating diffusion models for image denoising is not straightforward and requires solving several critical problems. For one thing, the input inconsistency hinders the connection between diffusion models and image denoising. For another, the content inconsistency between the generated image and the desired denoised image introduces distortion. To tackle these problems, we present a novel strategy called the Diffusion Model for Image Denoising (DMID) by understanding and rethinking the diffusion model from a denoising perspective. Our DMID strategy includes an adaptive embedding method that embeds the noisy image into a pre-trained unconditional diffusion model and an adaptive ensembling method that reduces distortion in the denoised image. Our DMID strategy achieves state-of-the-art performance on both distortion-based and perception-based metrics, for both Gaussian and real-world image denoising.The code is available at https://github.com/Li-Tong-621/DMID.