面向高动态范围成像的内容恢复和鬼影抑制网络  

Missing Content Restoration and Ghosting Suppression Network for High Dynamic Range Imaging

作　　者：杨珍妹 李华锋[1] 张亚飞 YANG Zhenmei;LI Huafeng;ZHANG Yafei(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650504)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650504

出　　处：《模式识别与人工智能》2024年第4期313-327,共15页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.62161015);云南省基础研究项目(No.202301AV070004)资助。

摘　　要：基于多曝光融合的高动态范围(High Dynamic Range,HDR)成像旨在整合多幅低动态范围图像(Low Dynamic Range,LDR)的信息,以生成高质量的HDR图像.然而,抑制运动区域的鬼影信息和恢复过饱和区域的缺失信息仍是HDR成像面临的两大挑战.为了综合考虑对参考图像缺失内容的恢复和运动区域鬼影的抑制,文中提出面向HDR成像的内容恢复和鬼影抑制网络.在内容恢复方面,引入基于预测滤波的内容恢复块.由内容恢复块预测到的滤波核对参考图像特征进行滤波,整合参考图像和非参考图像中的关键信息,为有效进行缺失内容的重建提供更丰富的信息.为了抑制运动区域的鬼影信息并充分利用非参考图像中的互补信息,引入可变形卷积,将非参考图像特征与参考图像特征对齐.此外,为了提升网络的HDR图像重建能力,构建三支路图像重建模块,包括一条主支路和两条辅助支路,辅助支路协助主支路在HDR结果的生成过程中更好地保留细节.实验表明,文中网络在主观视觉和客观指标上均具有较优表现.High dynamic range(HDR)imaging based on multi-exposure fusion aims to generate high-quality HDR images by integrating the information from multiple low dynamic range(LDR)images.However,HDR imaging is faced with two major challenges,ghosting artifact suppression in motion regions and lost information restoration in over-saturated areas.To comprehensively address the challenges of restoring missing content from reference images and suppressing ghosting artifacts in motion regions,a missing content restoration and ghosting suppression network for high dynamic range imaging is proposed in this paper.In terms of content restoration,a predictive filtering-based content restoration block is introduced.The filtering kernel predicted by the content restoration block is employed to filter reference image features,integrating key information from both reference images and non-reference images to provide richer information for effective reconstruction of missing content.To suppress ghosting artifacts in motion regions and fully exploit complementary information from non-reference images,deformable convolutions are introduced to align features from non-reference images with those from the reference image.Additionally,to enhance the HDR image reconstruction capability of the network,a three-branch image reconstruction module is constructed,including a main branch and two auxiliary branches.The auxiliary branches assist the main branch with better preserved details during the generation of HDR results.Experimental results demonstrate superior performance of the proposed network.

关 键 词：高动态范围成像 鬼影抑制 预测滤波 内容恢复 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]