基于即插即用分裂算法的盲图像修复扩散模型  

Blind Image Restoration Diffusion Model Based on Plug-and-play Splitting Algorithm

作　　者：侯骁伦 蔺素珍[1] 王彦博 王志茹 HOU Xiao-Lun;LIN Su-Zhen;WANG Yan-Bo;WANG Zhi-Ru(School of Computer Science and Technology,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学计算机科学与技术学院,太原030051

出　　处：《计算机系统应用》2025年第3期105-114,共10页Computer Systems & Applications

基　　金：国家自然科学基金(62271453);国家自然科学基金联合基金(U21A20524);山西省自然科学基金(202303021211147);山西省基础研究计划(20210302123025)。

摘　　要：针对现行即插即用图像修复方法无法处理弱光图像增强等盲图像修复任务中图像退化模型难以精确建模的问题,本文构造了一种将即插即用分裂算法与引导扩散模型相结合的求解方案.该方案巧妙地避免了直接求解由复杂退化模型导致的复杂数据子问题,转而使用真实退化图像来解决数据子问题,并利用数据子问题的解作为“锚点”间接约束并优化先验子问题的求解过程.从而确保了图像修复结果能够更紧密地贴近真实的图像恢复目标.本方法在多个公开数据集上进行验证,结果表明,所提算法与现行具有代表性的方法相比,PSNR和SSIM分别平均提升4.89%和9.48%.实验证明,所提方法在修复指标上表现更好,验证了本方法的有效性.In response to the problem that current plug-and-play image restoration methods cannot accurately model image degradation models in blind image restoration tasks such as low-light image enhancement,this study constructs a solution that combines a plug-and-play splitting algorithm with a guided diffusion model.This solution cleverly avoids directly solving complex data sub-problems caused by complex degradation models.Instead,it uses real degraded images to solve data sub-problems and takes the solutions of data sub-problems as“anchor points”to indirectly constrain and optimize the solving process of prior sub-problems.This ensures that the image restoration results can be more closely approximated to the real image restoration target.This method is validated on multiple public datasets.The results show that the proposed algorithm achieves an average improvement of 4.89%in PSNR and 9.48%in SSIM compared to current representative methods.Experiments prove that the proposed method performs better in repair metrics,validating its effectiveness.

关 键 词：图像修复 即插即用 扩散模型 非线性修复 深度学习 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]