文献类型：期刊文献

英文题名：SFDiff: Diffusion model with sufficient spatial-Fourier frequency information interaction for low-light image enhancement

作者：Wan, Fei[1,2];Xu, Bingxin[1,2,3];Yao, Jingli[1,2];Zeng, Lu[1,2];Pan, Weiguo[1,2];Liu, Hongzhe[1,2]

第一作者：Wan, Fei

通讯作者：Xu, BX[1]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing, Peoples R China;[3]97 Beisihuan East Rd, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China.|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

年份：2024

外文期刊名：IET IMAGE PROCESSING

收录：;EI(收录号：20244317242215);Scopus(收录号：2-s2.0-85206600231);WOS:【SCI-EXPANDED(收录号:WOS:001331876600001)】；

基金：This research was supported by Beijing Municipal Natural Science Foundation under Grant No. 4242020 and National Natural Science Foundation of China under Grant Nos. 62006020, No. 62171042 and No. 61871039.

语种：英文

外文关键词：diffusion; fast Fourier transforms; image enhancement; image processing

摘要：Diffusion models are increasingly applied in low-light image enhancement tasks due to their exceptional capability to model data distributions, but most current methods focus only on the original pixel space and neglect the potential of Fourier frequency information. In this article, SFDiff is proposed, a novel low-light image enhancement method that integrates Fourier frequency information into the diffusion process. Specifically, Fourier transforms are applied at both the image and feature levels to separately enhance the amplitude and phase components, which restores global illumination degradation and positional information. Then a Spatial-Frequency Fusion (SFF) block is used to fully integrate and interact with the information across spatial and frequency domains. Since illumination degradation is primarily manifested in the amplitude component, a loss function based on maximum likelihood learning is employed to constrain the amplitude component at each step of the sampling process, ensuring that the reverse process maintains an optimal trajectory. Owing to the streamlined network design and the fact that the Fourier transform requires no extra parameters, SFDiff achieves a reduction in parameters of over 35%$35\%$ compared to several state-of-the-art (SOTA) diffusion models and delivers high-quality enhancement results on multiple real-world datasets. The code is available at . This article proposes SFDiff, which incorporates Fourier frequency information into the diffusion process and facilitates sufficient interaction between spatial and frequency information for low-light image enhancement. image