CLE Diffusion: Controllable Light Enhancement Diffusion Model

TL;DR

CLE Diffusion is a novel diffusion-based framework that allows users to control the brightness and regions of enhancement in low light images, improving user experience and versatility.

Contribution

It introduces a controllable diffusion model with illumination embedding and SAM integration for region-specific enhancement, a novel approach in low light image enhancement.

Findings

Achieves competitive quantitative performance

Provides versatile user controllability

Demonstrates effective region-specific enhancement

Abstract

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/