Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
This addresses the need for practical low-light image enhancement without requiring paired data or high computational resources, though it is incremental as it builds on existing lookup table and diffusion model techniques.
The paper tackles the problem of low-light image enhancement by proposing an unsupervised framework that uses lookup tables and diffusion priors to recover images efficiently, outperforming state-of-the-art methods in visual quality and efficiency.
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.