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

作　　者：贾修一[1] 林乔万尼 郑卓然 石争浩[2] JIA Xiu-yi;LIN Qiao-wan-ni;ZHENG Zhuo-ran;SHI Zheng-hao(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing,Jiangsu 210094,China;School of Computer Science and Engineering,Xi’an University of Technology,Xi’an,Shaanxi 710048,China)

机构地区：[1]南京理工大学计算机科学与工程学院,江苏南京210094 [2]西安理工大学计算机科学与工程学院,陕西西安710048

出　　处：《电子学报》2025年第1期238-247,共10页Acta Electronica Sinica

基　　金：国家自然科学基金(No.62176123)。

摘　　要：随着超高清(Ultra-High-Definition,UHD)成像技术的应用,生成高质量的UHD图像通常需要融合多幅曝光水平不同的UHD图像.然而,目前基于深度学习的多曝光图像融合方法直接融合从不同曝光水平的图像中提取的特征图,未能充分利用不同曝光级别图像中的特征信息,而这些特征信息对于获得良好的多曝光融合结果至关重要.为解决这一问题,我们提出了一种新颖的UHD多曝光图像融合方法,该方法结合了图像的局部和长距离依赖特征,旨在挖掘不同曝光级别图像之间的依赖关系,提取出更高阶的语义和特征.进而,利用不同级别的短连接来聚合不同粒度的特征.最后,为了过滤带噪声的特征,我们还提出了带有门控机制的多层感知器来生成高质量的超高清图像.为了更好地展示实验结果,我们还针对多曝光融合任务建立了一个UHD图像数据集.实验结果表明,在单个显存24G的GPU上执行UHD多曝光图像融合任务时,我们的方法明显优于现有方法.With the deployment of ultra-high-definition(UHD)imaging technology,generating high-quality UHD images 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 images 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 granularity 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 significantly 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 

分 类 号：TP397.4[自动化与计算机技术—计算机应用技术]