液晶与显示2024，Vol.39Issue(6)：856-866,11.DOI:10.37188/CJLCD.2023-0210
跨级特征自适应融合的暗光图像增强算法
Cross-level feature adaptive fusion network for low-light image enhancement
摘要
Abstract
Aiming at the problems of low brightness,low contrast and poor visual effect in images collected in low-light environment,a low-light image enhancement algorithm based on cross-level adaptive feature fusion is proposed.Firstly,a network frontend is built by combining hierarchical sampling and large receptive field convolution to generate multi-scale features of large-area receptive fields,so that shallow information mining can be fully carried out.Secondly,a multi-head transposed attention module embedded in the middle of the network is introduced,the cross-covariance between channels is calculated to generate attention maps,and global context information associations are implicitly established.Thirdly,a joint loss function is constructed to correct the convergence direction of the model,assist the model optimized from the perspective of contrast and structure,and improve the robustness of the algorithm.Relevant experiments are carried out on the LOL and LOLv2 datasets.The experimental results show that the proposed algorithm outperforms most advanced algorithms in terms of objective indicators such as peak signal-to-noise ratio(PSNR)and structural similarity(SSIM).Subjectively,the image brightness is natural and the noise is low,and artifacts are effectively suppressed.关键词
低照度图像/广域卷积/多尺度/多头转置注意力/联合损失函数Key words
low-light image/large receptive field convolution/multi-scale/transformer/joint loss function分类
信息技术与安全科学引用本文复制引用
梁礼明,朱晨锟,阳渊,李仁杰..跨级特征自适应融合的暗光图像增强算法[J].液晶与显示,2024,39(6):856-866,11.基金项目
国家自然科学基金(No.51365017,No.61463018) （No.51365017,No.61463018）
江西省自然科学基金面上项目(No.20192BAB205084) （No.20192BAB205084）
江西省教育厅科学技术研究重点项目(No.GJJ170491)Supported by National Natural Science Foundation of China(No.51365017,No.61463018) （No.GJJ170491）
General Project of Natural Science Foundation of Jiangxi Province(No.20192BAB205084) （No.20192BAB205084）
Science and Technology Research Key Project of Education Department of Jiangxi Province(No.GJJ170491) （No.GJJ170491）
