Zero-Reference Lighting Estimation Diffusion Model for Low-Light Image Enhancement

TL;DR

This paper introduces Zero-LED, a zero-reference diffusion model for low-light image enhancement that reduces reliance on paired data and improves generalization by bridging low-light and normal-light domains.

Contribution

The proposed Zero-LED leverages diffusion models with zero-reference learning and bidirectional constraints, enabling effective low-light enhancement without paired training data.

Findings

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

Demonstrates strong generalization to various real-world scenes

Effectively bridges low-light and normal-light domains

Abstract

Diffusion model-based low-light image enhancement methods rely heavily on paired training data, leading to limited extensive application. Meanwhile, existing unsupervised methods lack effective bridging capabilities for unknown degradation. To address these limitations, we propose a novel zero-reference lighting estimation diffusion model for low-light image enhancement called Zero-LED. It utilizes the stable convergence ability of diffusion models to bridge the gap between low-light domains and real normal-light domains and successfully alleviates the dependence on pairwise training data via zero-reference learning. Specifically, we first design the initial optimization network to preprocess the input image and implement bidirectional constraints between the diffusion model and the initial optimization network through multiple objective functions. Subsequently, the degradation factors of the real-world scene are optimized iteratively to achieve effective light enhancement. In addition, we explore a frequency-domain based and semantically guided appearance reconstruction module that encourages feature alignment of the recovered image at a fine-grained level and satisfies subjective expectations. Finally, extensive experiments demonstrate the superiority of our approach to other state-of-the-art methods and more significant generalization capabilities. We will open the source code upon acceptance of the paper.