文献类型：期刊文献

英文题名：PSC diffusion: patch-based simplified conditional diffusion model for low-light image enhancement

作者：Wan, Fei[1,2];Xu, Bingxin[1,2];Pan, Weiguo[1,2];Liu, Hongzhe[1,2]

第一作者：Wan, Fei

通讯作者：Xu, BX[1];Xu, BX[2]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Coll Robot, 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;[2]corresponding author), Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：2024

卷号：30

期号：4

外文期刊名：MULTIMEDIA SYSTEMS

收录：;EI(收录号：20242616318973);Scopus(收录号：2-s2.0-85196626107);WOS:【SCI-EXPANDED(收录号:WOS:001251562700001)】；

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

语种：英文

外文关键词：Low-light image enhancement; Generative model; Diffusion model; U-Net; Image patching; Parameter-free attention

摘要：Low-light image enhancement is pivotal for augmenting the utility and recognition of visuals captured under inadequate lighting conditions. Previous methods based on Generative Adversarial Networks (GAN) are affected by mode collapse and lack attention to the inherent characteristics of low-light images. This paper propose the Patch-based Simplified Conditional Diffusion Model (PSC Diffusion) for low-light image enhancement due to the outstanding performance of diffusion models in image generation. Specifically, recognizing the potential issue of gradient vanishing in extremely low-light images due to smaller pixel values, we design a simplified U-Net architecture with SimpleGate and Parameter-free attention (SimPF) block to predict noise. This architecture utilizes parameter-free attention mechanism and fewer convolutional layers to reduce multiplication operations across feature maps, resulting in a 12-51% reduction in parameters compared to U-Nets used in several prominent diffusion models, which also accelerates the sampling speed. In addition, preserving intricate details in images during the diffusion process is achieved through employing a patch-based diffusion strategy, integrated with global structure-aware regularization, which effectively enhances the overall quality of the enhanced images. Experiments show that the method proposed in this paper achieves richer image details and better perceptual quality, while the sampling speed is over 35% faster than similar diffusion model-based methods.