Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement

TL;DR

This paper introduces BDCE, a bootstrap diffusion model that efficiently estimates curve parameters for high-resolution low-light image enhancement, simultaneously improving performance and reducing computational costs.

Contribution

The paper presents a novel bootstrap diffusion approach for curve estimation, enabling effective high-resolution low-light image enhancement with integrated denoising.

Findings

Achieves state-of-the-art results on benchmark datasets.

Reduces computational cost compared to existing methods.

Effectively combines enhancement and denoising in high-resolution images.

Abstract

Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational cost in high resolution images and unsatisfactory performance in simultaneous enhancement and denoising. To address these problems, we propose BDCE, a bootstrap diffusion model that exploits the learning of the distribution of the curve parameters instead of the normal-light image itself. Specifically, we adopt the curve estimation method to handle the high-resolution images, where the curve parameters are estimated by our bootstrap diffusion model. In addition, a denoise module is applied in each iteration of curve adjustment to denoise the intermediate enhanced result of each iteration. We evaluate BDCE on commonly used benchmark datasets, and extensive experiments show that it achieves state-of-the-art qualitative and quantitative performance.