基于深度可分离选择性残差网络的真实图像增强算法  

Realistic image enhancement algorithm based on depth⁃separable selective residual network

作　　者：温剑 邵剑飞[1] 邵建龙[1] WEN Jian;SHAO Jianfei;SHAO Jianlong(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《现代电子技术》2023年第7期52-56,共5页Modern Electronics Technique

基　　金：国家自然科学基金项目(61732005);云南省重大科技专项计划项目(202002AD080001)。

摘　　要：图像去噪作为低级视觉任务,在图像处理领域常被重点研究。针对图像去噪网络训练周期长和图像纹理细节模糊的问题,为提升图像去噪效果,减少训练参数量,缩短训练周期,提出了一种改进M⁃Net网络融合深度可分离卷积及选择性残差网络的图像盲去噪方法。所提方法在两个合成数据集和两个真实世界噪声数据集上的定量指标及视觉质量评价均达到对比去噪算法的性能,同时具有更小的FLOPs。Image denoising,as a low⁃level vision task,is often studied emphaticallyin the field of image processing.In allusion to the problems of long training period of image denoising network and blurred image texture details,a blind image denoising method improving the M⁃Net network fusing depth⁃separable convolution and selective residual networks is proposed to improve the image denoising effect,reduce the number of training parameters and shorten the training period.The proposed method achieves the performance of comparative denoising algorithms in terms of quantitative metrics and visual quality evaluation on two synthetic datasets and two real⁃world noisy datasets,and also has smaller FLOPs.

关 键 词：图像增强 图像盲去噪 残差网络 视觉质量评价 特征融合 深度可分离卷积 去噪模型 图像边缘保护 

分 类 号：TN911.73-34[电子电信—通信与信息系统]