提示学习与门控前馈网络的多尺度图像去模糊  

Multiscale image deblurring based on prompt learning and gated feedforward networks

作　　者：谢斌[1] 黎彦先 邵祥 戴邦强 Xie Bin;Li Yanxian;Shao Xiang;Dai Bangqiang(School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学信息工程学院,赣州341000

出　　处：《中国图象图形学报》2025年第3期755-768,共14页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61972264);江西省自然科学基金项目(20192BAB207036);江西理工大学博士启动基金项目(20520010058)。

摘　　要：目的针对传统基于深度学习的去模糊方法存在的伪影明显、细节模糊和噪声残留等问题,提出一种基于提示学习的多尺度图像去模糊新方法。方法首先,在详细分析传统去模糊方法的基础上,引入基于提示学习的特定退化信息编码模块,利用退化信息中包含的上下文信息来动态地引导深度网络以更有效地完成去模糊任务。其次,设计了新的门控前馈网络,通过控制各个层级的信息流动构建更为丰富和更具层次结构的特征表示,从而进一步提高对复杂数据的理解和处理能力,以更好地保持结果图像的几何结构。另外,新方法引入了经典的总变差正则来抑制去模糊过程中的噪声残留,以提高结果图像的视觉表现。结果基于GoPro和REDS(the realistic and diverse scenes)数据集的大量实验结果表明,与其他先进的基于深度学习的去模糊方法相比,本文方法在图像去模糊方面取得了更好的效果。在峰值信噪比(peak signal-to-noise ratio,PSNR)和结构相似性(structural similarity,SSIM)指标上,本文方法在GoPro数据集上分别达到33.04 dB和0.962的最优结果。在REDS数据集上分别达到28.70 dB和0.859的结果。并且,相比SAM-deblur(segment anything model-deblur)方法,PSNR提升了1.77 dB。结论相较于其他的去模糊方法,本文方法不仅能够较好地保持结果图像的细节信息,而且还能够有效地克服伪影明显和噪声残留的问题,所得结果图像在PSNR和SSIM等客观评价指标方面均有更好的表现。Objective Image deblurring aims to restore a clean image from blurry images while still maintaining the structure and details of the original image during the restoration.With the rapid development of Internet technology,the way people obtain images becomes highly diversified.However,the image is often blurred or distorted by various factors during the acquisition process.Therefore,deblurring the image is necessary.Image deblurring is of considerable importance to improve image quality and plays a key role in numerous fields such as medical imaging,satellite image processing,and security monitoring,which has attracted the attention of many researchers.Additional prior knowledge is needed to recover images with high quality due to the ill-posed image deblurring task.At present,the existing deblurring methods include traditional and deep learning-based approaches.In the traditional methods,despite the simplicity and convenience of the filter-based deblurring method,the recovered images often have artifacts,content loss,and other problems,which fail to meet the needs of various applications.The deblurring method based on the idea of regularity has received increasing attention from researchers for a long time,and various methods of constructing regular terms have been proposed to solve this kind of ill-posed problems.These traditional methods can achieve the purpose of deblurring to a certain extent.However,they rely on the prior information of images,which is difficult to obtain accurately in practical applications.Therefore,this kind of method cannot be effectively promoted in a wide range.With the extensive application of deep learning technology,an increasing number of researchers begin to use this technology to address ill-posed problems.The image deblurring methods generally fall into three main categories:convolutional neural network(CNN)-based method,generative adversarial network(GAN)-based method,and Transformer-based method.In the CNN-based methods,the powerful feature extraction capability of CNNs allows

关 键 词：图像去模糊 提示学习 多尺度 门控前馈网络(GFFN) 深度卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]