电子学报2025，Vol.53Issue(1)：238-247,10.DOI:10.12263/DZXB.20230840
基于稠密局部-全局特征融合的超高清多曝光图像融合方法
UHD Multi-Exposure Image Fusion via Dense Local-Global Feature Aggregation
摘要
Abstract
With the deployment of ultra-high-definition(UHD)imaging technology,generating high-quality UHD im-ages typically involves fusing multiple UHD images with varying exposure levels.However,current multi-exposure image fusion(MEF)methods based on deep learning perform direct fusion of feature maps extracted from images with different exposure levels.These methods fail to fully exploit the feature information in images with varying exposure levels,which is essential for achieving successful MEF outcomes.To address this problem,we develop a UHD multi-exposure image fusion approach that incorporates both local and long-range characteristics of images,and it aims to mine the dependencies of im-ages with different exposure levels.By enforcing translation invariance and self-attention on images with varying exposure levels,we can extract higher-level semantics and features.Furthermore,we aggregate the resulting features of different gran-ularity by utilizing shortcut connections at various levels.Finally,we propose the Gate-MLP with a gating mechanism for filtering features with noise to generate a high-quality UHD image.To better demonstrate the work for UHD MEF task,we also establish a UHD image dataset for MEF task.Extensive experimental results demonstrate that ourapproach significant-ly outperforms existing approaches for UHD multi-exposure image fusion task on a single 24G RAM GPU.关键词
超高清图像/多曝光图像融合/稠密特征融合/双分支/实时处理Key words
UHD images/multi-exposure image fusion/dense feature aggregation/dual-branch/real-time processing分类
计算机与自动化引用本文复制引用
贾修一,林乔万尼,郑卓然,石争浩..基于稠密局部-全局特征融合的超高清多曝光图像融合方法[J].电子学报,2025,53(1):238-247,10.基金项目
国家自然科学基金(No.62176123) National Natural Science Foundation of China(No.62176123) （No.62176123）
