摘要
针对现有低照度图像增强算法难以同时处理亮度、对比度、伪影和噪声等因素,提出了多分支残差与仿射变换低光增强网络,其核心思想是运用不同模块处理不同的任务。首先通过光照估计模块获得低光图像的光照变量,然后使光照仿射变换模块与光照编码参数融合恢复图像的光照,最后通过细节重建模块融合更多的图像细节获得最终输出。实验结果表明,该方法有效地丰富了图像的纹理细节,同时增强了亮度和对比度,并具有更少的伪影和噪声。通过与其他主流方法进行比较,定量和定性地证明了提出方法对低光图像增强的效果更好。
The existing algorithms cannot deal with brightness,contrast,artifact and noise at the same time.This paper proposed the low-light enhancement network based on multi-branch residual and affine transformation.The key idea was to exert different modules to handle different tasks.Firstly,the illumination estimation module obtained the illumination variable of the low-light image.Secondly,it combined the illumination affine transformation module with the illumination encoding parameters to restore the illumination of the image.Finally,the detail reconstruction module fused more image details to obtain the final output.The experimental results show that the proposed method effectively enriches the image texture details,enhances brightness and contrast while suppressing the artifact and noise generated.Compared with popular methods,the results quantitatively and qualitatively prove that the method is better for low-light image enhancement.
作者
黄仁婧
崔虎
陈青梅
黄初华
Huang Renjing;Cui Hu;Chen Qingmei;Huang Chuhua(College of Computer Science&Technology,Guizhou University,Guiyang 550025,China)
出处
《计算机应用研究》
CSCD
北大核心
2021年第12期3786-3790,3807,共6页
Application Research of Computers
基金
贵州省自然科学基金资助项目(黔科合基础[2019]1088)
贵州大学引进人才科研项目(贵大人基合字(2017)31号
贵大人基合字(2015)52号)。
关键词
低照度图像增强
光照估计
仿射变换
图像融合
多分支独立并行残差结构
low-light image enhancement
illumination estimation
affine transformation
image fusion
multi-branch independent parallel residual structure
