CLE Diffusion: Controllable Light Enhancement Diffusion Model
This work addresses the need for more user-controllable enhancement in visual creation and editing, offering incremental improvements over existing homogeneous methods.
The paper tackles the problem of low light enhancement by proposing CLE Diffusion, a diffusion framework that allows users to control brightness levels and specify regions for enhancement, achieving competitive performance in quantitative metrics and qualitative results.
Low light enhancement has gained increasing importance with the rapid development of visual creation and editing. However, most existing enhancement algorithms are designed to homogeneously increase the brightness of images to a pre-defined extent, limiting the user experience. To address this issue, we propose Controllable Light Enhancement Diffusion Model, dubbed CLE Diffusion, a novel diffusion framework to provide users with rich controllability. Built with a conditional diffusion model, we introduce an illumination embedding to let users control their desired brightness level. Additionally, we incorporate the Segment-Anything Model (SAM) to enable user-friendly region controllability, where users can click on objects to specify the regions they wish to enhance. Extensive experiments demonstrate that CLE Diffusion achieves competitive performance regarding quantitative metrics, qualitative results, and versatile controllability. Project page: https://yuyangyin.github.io/CLEDiffusion/