真实复杂场景下基于残差收缩网络的单幅图像超分辨率方法  

Single image super-resolution method based on residual shrinkage network in real complex scenes

作　　者：李颖 黄超 孙成栋 徐勇 LI Ying;HUANG Chao;SUN Chengdong;XU Yong(College of Computer Science and Technology,Harbin Institute of Technology,Shenzhen,Shenzhen Guangdong 518055,China;Shenzhen Key Laboratory of Visual Object Detection and Recognition(Harbin Institute of Technology,Shenzhen),Shenzhen Guangdong 518055,China)

机构地区：[1]哈尔滨工业大学(深圳)计算机科学与技术学院,广东深圳518055 [2]深圳市视觉目标检测与判识重点实验室(哈尔滨工业大学(深圳)),广东深圳518055

出　　处：《计算机应用》2023年第12期3903-3910,共8页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61876051);深圳市科创委资助项目(JSGG20220831104402004)。

摘　　要：真实世界中极少存在成对的高低分辨率图像对,传统的基于图像对训练模型的单幅图像超分辨率(SR)方法采用合成数据集的方式得到训练集时仅考虑了双线性下采样退化,且传统图像超分辨率方法在面向真实的未知退化图像时重建效果较差。针对上述问题,提出一种面向真实复杂场景的图像超分辨率方法。首先,采用不同焦距对景物进行拍摄并配准得到相机采集的真实高低分辨率图像对,构建一个场景多样的数据集CSR(Camera Super-Resolution dataset);其次,为了尽可能地模拟真实世界中的图像退化过程,根据退化因素参数随机化和非线性组合退化改进图像退化模型,并且结合高低分辨率图像对数据集和图像退化模型以合成训练集;最后,由于数据集中考虑了退化因素,引入残差收缩网络和U-Net改进基准模型,尽可能地减少退化因素在特征空间中的冗余信息。实验结果表明,所提方法在复杂退化条件下相较于次优BSRGAN(Blind Super-Resolution Generative Adversarial Network)方法,在RealSR和CSR测试集中PSNR指标分别提高了0.7 dB和0.14 dB,而SSIM分别提高了0.001和0.031。所提方法在复杂退化数据集上的客观指标和视觉效果均优于现有方法。There are very few paired high and low resolution images in the real world.The traditional single image Super-Resolution(SR)methods typically use pairs of high-resolution and low-resolution images to train models,but these methods use the way of synthetizing dataset to obtain training set,which only consider bilinear downsampling as image degradation process.However,the image degradation process in the real word is complex and diverse,and traditional image super-resolution methods have poor reconstruction performance when facing real unknown degraded images.Aiming at those problems,a single image super-resolution method was proposed for real complex scenes.Firstly,high-and low-resolution images were captured by the camera with different focal lengths,and these images were registered as image pairs to form a dataset CSR(Camera Super-Resolution dataset)of various scenes.Secondly,to simulate the image degradation process in the real world as much as possible,the image degradation model was improved by the parameter randomization of degradation factors and the nonlinear combination degradation.Besides,the dataset of high-and low-resolution image pairs and the image degradation model were combined to synthetize training set.Finally,as the degradation factors were considered in the dataset,residual shrinkage network and U-Net were embedded into the benchmark model to reduce the redundant information caused by degradation factors in the feature space as much as possible.Experimental results indicate that compared with the BSRGAN(Blind Super-Resolution Generative Adversarial Network)method,under complex degradation conditions,the proposed method improves the PSNR by 0.7 dB and 0.14 dB,and improves SSIM by 0.001 and 0.031 respectively on the RealSR and CSR test sets.The proposed method has better objective indicators and visual effect than the existing methods on complex degradation datasets.

关 键 词：超分辨率 复杂场景 图像退化模型 残差收缩网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]