Global Structure-Aware Diffusion Process for Low-Light Image Enhancement

TL;DR

This paper introduces a global structure-aware diffusion framework for low-light image enhancement, utilizing curvature and uncertainty regularization to improve detail preservation, contrast, and noise suppression.

Contribution

It proposes a novel diffusion-based method with curvature and uncertainty-guided regularization, enhancing low-light images more effectively than existing techniques.

Findings

Significant improvement in image quality and contrast

Enhanced noise suppression and detail preservation

Outperforms state-of-the-art methods in low-light enhancement

Abstract

This paper studies a diffusion-based framework to address the low-light image enhancement problem. To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory. To be specific, inspired by the recent research that low curvature ODE-trajectory results in a stable and effective diffusion process, we formulate a curvature regularization term anchored in the intrinsic non-local structures of image data, i.e., global structure-aware regularization, which gradually facilitates the preservation of complicated details and the augmentation of contrast during the diffusion process. This incorporation mitigates the adverse effects of noise and artifacts resulting from the diffusion process, leading to a more precise and flexible enhancement. To additionally promote learning in challenging regions, we introduce an uncertainty-guided regularization technique, which wisely relaxes constraints on the most extreme regions of the image. Experimental evaluations reveal that the proposed diffusion-based framework, complemented by rank-informed regularization, attains distinguished performance in low-light enhancement. The outcomes indicate substantial advancements in image quality, noise suppression, and contrast amplification in comparison with state-of-the-art methods. We believe this innovative approach will stimulate further exploration and advancement in low-light image processing, with potential implications for other applications of diffusion models. The code is publicly available at https://github.com/jinnh/GSAD.