Diffusion Priors for Variational Likelihood Estimation and Image Denoising

TL;DR

This paper introduces a novel approach using diffusion priors with adaptive likelihood estimation and MAP inference to effectively denoise real-world images with structured, signal-dependent noise, surpassing previous methods.

Contribution

It proposes a new diffusion prior-based framework with adaptive likelihood and MAP inference for real-world image denoising, addressing limitations of prior approaches.

Findings

Effective removal of structured, real-world noise.

Outperforms existing methods on diverse datasets.

Enables direct high-resolution image denoising.

Abstract

Real-world noise removal is crucial in low-level computer vision. Due to the remarkable generation capabilities of diffusion models, recent attention has shifted towards leveraging diffusion priors for image restoration tasks. However, existing diffusion priors-based methods either consider simple noise types or rely on approximate posterior estimation, limiting their effectiveness in addressing structured and signal-dependent noise commonly found in real-world images. In this paper, we build upon diffusion priors and propose adaptive likelihood estimation and MAP inference during the reverse diffusion process to tackle real-world noise. We introduce an independent, non-identically distributed likelihood combined with the noise precision (inverse variance) prior and dynamically infer the precision posterior using variational Bayes during the generation process. Meanwhile, we rectify the estimated noise variance through local Gaussian convolution. The final denoised image is obtained by propagating intermediate MAP solutions that balance the updated likelihood and diffusion prior. Additionally, we explore the local diffusion prior inherent in low-resolution diffusion models, enabling direct handling of high-resolution noisy images. Extensive experiments and analyses on diverse real-world datasets demonstrate the effectiveness of our method. Code is available at https://github.com/HUST-Tan/DiffusionVI.