摘要
以往基于卷积神经网络的图像超分辨率算法往往是在理想的合成数据进行训练,当应用在真实世界(Real-World)场景时性能就会严重下降。为更好地提取出Real-World图像中的原有特征信息,为其降质过程建模,提出一种噪声和U型判别网络的Real-World图像超分辨率算法。利用直接收集到的Real-World图像原有的复杂噪声信息,结合合成的降质图像,达到降质后图像与源图像保持特征分布相似的目的,以恢复更多的细节信息和更好的观感。此外,提出使用频谱归一正则化的U型判别网络,以提高判别网络的能力和稳定训练,抑制图像重建中伪影的出现。在三个基准数据集上的实验结果表明,与最新的方法相比,该模型在三个评价指标(峰值信噪比、结构相似度和感知图像块相似度)上均取得了最好的结果,且有着更好的观感效果。
Previous image super-resolution algorithms based on convolutional neural networks are usually trained on syn-thetic ideal datasets,and their performance will drop dramatically in real-world scenarios.To better extract the original feature information in real-world images and model their degradation process,this paper proposes a real-world image super resolution reconstruction based on noise and U-shape discrimination network.To make the degraded image having a simi-lar feature distribution to the source image and restoring more detailed information and better visual quality,this paper uses the complex noise information directly collected from the source real-world image to inject the synthetic degraded image.In addition,this paper proposes to employ a U-shape discrimination network with spectral normalization to increase the discrimination network capability and stabilize the training,and suppress the appearance of artifacts in image reconstruc-tion.Experimental results on three benchmark datasets show that compared with the state-of-the-art methods,this model achieves the best results in all three evaluation protocols(peak signal-to-noise ratio(PSNR),structural similarity(SSIM),and learned perceptual image patch similarity(LPIPS))and has better visual quality.
作者
李灏
杨志景
王美林
凌永权
LI Hao;YANG Zhijing;WANG Meilin;LING Wing-Kuen(School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,China)
出处
《计算机工程与应用》
CSCD
北大核心
2023年第6期204-211,共8页
Computer Engineering and Applications
基金
国家自然科学基金(U1701266)
广东省自然科学基金(2021A1515011341)
广州市科技计划项目(202002030386)。
关键词
超分辨率
真实世界图像
噪声
降质过程
U型判别网络
super-resolution
real-world image
noise
degradation processing
U-shape discrimination network
