混合U型网络与Transformer的图像去模糊  

Hybrid U-shaped network and Transformer for image deblurring

作　　者：陈清江[1] 邵菲 王炫钧 CHEN Qing-jiang;SHAO Fei;WANG Xuan-jun(College of Science,Xi’an University of Architecture and Technology,Xi’an 710055,China)

机构地区：[1]西安建筑科技大学理学院,陕西西安710055

出　　处：《计算机工程与科学》2024年第10期1843-1851,共9页Computer Engineering & Science

基　　金：国家自然科学基金(12202332,61902304);陕西省自然科学基础研究计划(2021JQ-495)。

摘　　要：针对现有去模糊方法不能有效地恢复图像精细细节的问题,提出了一种混合U型网络与Transformer的图像去模糊方法。首先,使用一个多尺度特征提取模块提取图像的浅层特征信息。然后,通过一个含逐级特征增强模块的层级嵌套U型子网络,在保留图像细节信息的同时获取图像深层特征信息。再次,构建了一个局部-全局残差细化模块,通过卷积神经网络和SwinTransformer之间的信息交互充分提取全局和局部信息,并实现特征信息的进一步细化。最后,使用一个1×1卷积层进行特征重建。所提方法在GoPro数据集上的实验结果显示,图像的峰值信噪比和结构相似度均值分别为32.92和0.964,均优于其他对比方法。实验结果表明,所提方法可以有效地去除模糊,重建出具有丰富细节的潜在清晰图像。To address the problem that existing deblurring methods cannot effectively restore fine details of images,an image deblurring method combining a U-shaped network and Transformer is proposed.Firstly,a multi-scale feature extraction module is used to extract shallow feature information from the image.Then,a hierarchical nested U-shaped subnet with a stepwise feature enhancement module is employed to obtain deep feature information while preserving image detail information.Next,a local-global residual refinement module is constructed,which fully extracts global and local information through information interaction between convolutional neural networks and Swin Transformer,and further refines the feature information.Finally,a 1×1 convolutional layer is used for feature reconstruction.The proposed method achieves a peak signal-to-noise ratio(PSNR)of 32.92 and a structural similarity index mean(SSIM)of 0.964 on the GoPro dataset,both outperforming other comparative methods.Experimental results demonstrate that the proposed method can effectively remove blur and reconstruct a potentially clear image with rich details.

关 键 词：图像去模糊 细节信息 层级嵌套U型子网络 TRANSFORMER 多尺度特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]