Skip to content

lodew920/ERetinex

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement(ICRA2025)

简介

Low-light image enhancement aims to restore under-exposed images captured in dark scenarios. Traditional frame-based cameras often fail to capture structure and color information due to exposure time limitations, while event cameras, with their high dynamic range (HDR) and asynchronous response to brightness changes, excel in extreme low-light conditions. Inspired by the Retinex theory, we propose ERetinex, the first framework combining Retinex theory with event cameras for low-light image restoration. Our method leverages event cameras' high temporal resolution to accurately estimate scene illumination and fuses HDR data with traditional image color information to enhance image quality. Experimental results show that ERetinex outperforms state-of-the-art methods, achieving a 1.0613 dB gain in PSNR while reducing FLOPS by 84.28%.

环境依赖

数据集

代码结构

使用方法

训练

测试

参数说明

实验结果

引用

许可证

联系方式

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors