深度特征维纳反卷积用于均匀离焦盲去模糊  

Uniform defocus blind deblurring based on deeper feature-based wiener deconvolution

作　　者：王成曦 罗晨[2] 周江澔 邹浪 贾磊 WANG Chengxi;LUO Chen;ZHOU Jianghao;ZOU Lang;JIA Lei(School of Software Engineering,Southeast University,Suzhou 215123,China;School of Mechanical Engineering,Southeast University,Nanjin 211189,China;Wuxi shangshi-finevision Technology Co.,Ltd,Wuxi 200240,China)

机构地区：[1]东南大学软件学院,江苏苏州215123 [2]东南大学机械工程学院,江苏南京211189 [3]无锡尚实电子科技有限公司,江苏无锡200240

出　　处：《光学精密工程》2023年第18期2713-2722,共10页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.51975119);无锡市“太湖之光”科技攻关(产业前瞻及关键技术研发)项目资助(No.G20222011)。

摘　　要：工业精密制造中,视觉检测设备的成像系统往往景深较小,易产生离焦模糊,严重影响检测效果。针对这一问题,提出了一种针对于均匀离焦图像的盲去模糊网络(Uniform Defocus Blind Deblur Net,UDBD-Net)。首先,提出一种模糊核估计网络,提取离焦模糊的特征,并准确地估计出模糊核;其次,提出一种反卷积网络,通过神经网络学习并估计基于特征维纳反卷积(Feature-based Wiener Deconvolution,FWD)公式中的未知量,更准确地生成去模糊图像的潜在特征;最后,使用一个编解码网络(Encoder-Decoder Net)增强图像的细节,并去除伪影。实验结果表明,该方法在DIV2K和GOPRO图片上的峰值信噪比(Peak Signal to Noise Ratio,PSNR)分别达到31.16 dB和36.16 dB;与目前主流的方法相比,该方法在不显著增加模型推理时间的同时能够复原出更高质量、更自然地去模糊图像。此外,该方法对真实的均匀离焦模糊图像也有较好的去模糊效果,且能够显著提升工业视觉检测算法对于离焦模糊图像的检测效果。In industrial precision manufacturing,the small field depths of the imaging systems of visual in⁃spection equipment can make them susceptible to defocus blurring.This significantly degrades their detec⁃tion effect.To address this issue,this paper proposes a uniform defocus blind deblurring network(UDBDNet).First,a uniform defocus blur kernel estimation net for extracting the characteristics of out-of-focus blurring and accurately estimating the blur kernel is proposed.Second,a non-blind deconvolution net⁃work,which is used for learning and estimating the unknown quantity in the feature-based Wiener deconvo⁃lution(FWD)formula so as to accurately generate the latent features of blurred images,is presented.Finally,the use of an encoder-decoder net to enhance the details of the recovered image and remove the ar⁃tifacts is detailed.The experimental results indicate peak signal-to-noise ratio(PSNR)values of 31.16 dB and 36.16 dB for UDBD-Net on the images of DIV2K and GOPRO test sets,respectively.Compared with extant blind deblurring methods,the proposed method can restore deblurred images with higher quali⁃ty and more naturalness without significantly increasing the model inference time.Furthermore,UDBD-Net can achieve a good deblurring effect on real uniformly defocused blurred images and can considerably improve the detection effect of industrial vision detection algorithms on such images.

关 键 词：计算机视觉 盲去模糊 模糊核估计 反卷积 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]