基于循环神经网络的散焦图像去模糊算法  

Defocus deblurring algorithm based on deep recurrent neural network

作　　者：程文涛 任冬伟 王旗龙 Cheng Wentao;Ren Dongwei;Wang Qilong(College of Intelligence&Computing,Tianjin University,Tianjin 300350,China;School of Computer Science&Technology,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]天津大学智能与计算学部,天津300350 [2]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001

出　　处：《计算机应用研究》2022年第7期2203-2209,共7页Application Research of Computers

基　　金：国家自然科学基金资助项目(62172127,61801326)。

摘　　要：近年来,基于深度学习的运动模糊去除算法得到了广泛关注,然而单幅散焦图像去模糊算法鲜有研究。为针对性地解决单幅图像的散焦模糊问题,提出一种基于循环神经网络的散焦图像去模糊算法。首先级联两个残差网络,分别完成散焦图估计和图像去模糊;随后,为了保证散焦图和清晰图像的深度特征可以更好地跨阶段传播以及阶段内相互作用,在残差网络中引入LSTM(long short-term memory)循环层;最后,整个残差网络进行了多次迭代,迭代过程中网络参数共享。为了训练网络,制作了一个合成散焦图像数据集,每一张散焦图像都包含对应的清晰图像和散焦图。实验结果表明,该算法相较于对比算法在主客观图像质量评价上均有显著优势,在复原结果中具有更锐利的边缘和清晰的细节。对于真实双像素图像散焦模糊数据集DPD,该算法相比DPDNet-Single在峰值信噪比(PSNR)和结构相似性(SSIM)上分别提高了0.77 dB、5.6%,因此所提方法可以有效处理真实场景散焦模糊。Recent years,the motion deblurring algorithm based on deep learning has been widely concerned,while single defocus image deblurring is rarely studied.In order to specifically solve the defocus blur problem of single image,this paper proposed a defocus deblurring algorithm based on deep recurrent neural network.Firstly,the algorithm used two cascaded residual networks to estimate the defocus map and image deblurring,respectively.After that,to ensure that the depth features of defocus map and clear images could better propagate across stages and interact within stages,the algorithm introduced LSTM(long short-term memory)as a recurrent layer in the residual network.Finally,the whole residual network underwent several iterations and reused the network parameters during the iterative stages.To train the network,this paper produced a synthetic defocus blur image dataset,where each defocus blurred image contained a corresponding clear image and defocus map.The experimental results show that,compared with existing defocus deblurring methods,the proposed algorithm has significant advantages in both the subjective and objective image quality evaluation,and can produce sharper edges and clear details in the restoration results.On the real defocus blur dual-pixel image dataset DPD,the proposed algorithm improves the peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)by 0.77 dB and 5.6%,respectively,compared with DPDNet-Single.Therefore,the proposed method can effectively deal with defocus blur in real scenes.

关 键 词：图像去模糊 散焦模糊 散焦图估计 循环神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]