Single-Stage Signal Attenuation Diffusion Model for Low-Light Image Enhancement and Denoising

TL;DR

The paper introduces a single-stage diffusion model that simultaneously enhances brightness and suppresses noise in low-light images by integrating signal attenuation into the diffusion process.

Contribution

It proposes the Signal Attenuation Diffusion Model (SADM), which encodes physical priors of low-light degradation for unified image enhancement and denoising without extra modules.

Findings

SADM achieves simultaneous brightness enhancement and noise reduction.

The model maintains consistency with DDIM via multi-scale pyramid sampling.

Experimental results demonstrate improved performance over existing methods.

Abstract

Diffusion models excel at image restoration via probabilistic modeling of forward noise addition and reverse denoising, and their ability to handle complex noise while preserving fine details makes them well-suited for Low-Light Image Enhancement (LLIE). Mainstream diffusion based LLIE methods either adopt a two-stage pipeline or an auxiliary correction network to refine U-Net outputs, which severs the intrinsic link between enhancement and denoising and leads to suboptimal performance owing to inconsistent optimization objectives. To address these issues, we propose the Signal Attenuation Diffusion Model (SADM), a novel diffusion process that integrates the signal attenuation mechanism into the diffusion pipeline, enabling simultaneous brightness adjustment and noise suppression in a single stage. Specifically, the signal attenuation coefficient simulates the inherent signal attenuation of low-light degradation in the forward noise addition process, encoding the physical priors of low-light degradation to explicitly guide reverse denoising toward the concurrent optimization of brightness recovery and noise suppression, thereby eliminating the need for extra correction modules or staged training relied on by existing methods. We validate that our design maintains consistency with Denoising Diffusion Implicit Models(DDIM) via multi-scale pyramid sampling, balancing interpretability, restoration quality, and computational efficiency.