Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

TL;DR

This paper introduces an unsupervised low-light image enhancement method using lookup tables and diffusion priors, achieving efficient and high-quality results without requiring paired training data.

Contribution

The novel DPLUT framework combines lookup tables with diffusion priors for unsupervised low-light image enhancement, reducing reliance on large datasets and computational resources.

Findings

Outperforms state-of-the-art methods in visual quality

Achieves higher efficiency in low-light image enhancement

Effectively suppresses noise using diffusion priors

Abstract

Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. As a result, their practicality is limited. In this work, we devise a novel unsupervised LIE framework based on diffusion priors and lookup tables (DPLUT) to achieve efficient low-light image recovery. The proposed approach comprises two critical components: a light adjustment lookup table (LLUT) and a noise suppression lookup table (NLUT). LLUT is optimized with a set of unsupervised losses. It aims at predicting pixel-wise curve parameters for the dynamic range adjustment of a specific image. NLUT is designed to remove the amplified noise after the light brightens. As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in terms of visual quality and efficiency.