摘要
目的现有的基于深度学习的单帧图像超分辨率重建算法大多采用均方误差损失作为目标优化函数,以期获得较高的图像评价指标,然而重建出的图像高频信息丢失严重、纹理边缘模糊,难以满足主观视觉感受的需求。同时,现有的深度模型往往通过加深网络的方式来获得更好的重建效果,导致梯度消失问题的产生,训练难度增加。为了解决上述问题,本文提出融合感知损失的超分辨率重建算法,通过构建以生成对抗网络为主体框架的残差网络模型,提高了对低分率图像的特征重构能力,高度还原图像缺失的高频语义信息。方法本文算法模型包含生成器子网络和判别器子网络两个模块。生成器模块主要由包含稠密残差块的特征金字塔构成,每个稠密残差块的卷积层滤波器大小均为3×3。通过递进式提取图像不同尺度的高频特征完成生成器模块的重建任务。判别器模块通过在多层前馈神经网络中引入微步幅卷积和全局平均池化,有效地学习到生成器重建图像的数据分布规律,进而判断生成图像的真实性,并将判别结果反馈给生成器。最后,算法对融合了感知损失的目标函数进行优化,完成网络参数的更新。结果本文利用峰值信噪比(PSNR)和结构相似度(SSIM)两个指标作为客观评价标准,在Set5和Set14数据集上测得4倍重建后的峰值信噪比分别为31. 72 d B和28. 34 d B,结构相似度分别为0. 892 4和0. 785 6,与其他方法相比提升明显。结论结合感知损失的生成式对抗超分辨率重建算法准确恢复了图像的纹理细节,能够重建出视觉上舒适的高分辨率图像。
Objective Single image super-resolution(SISR)is a research hotspot in computer vision.SISR aims to reconstruct a high-resolution image from its low-resolution counterpart and is widely used in video surveillance,remote sensing image,and medical imaging.In recent years,many researchers have concentrated on convolutional SISR networking to the massive development of deep learning.They constructed shallow convolutional networks,which perform poorly in improving the quality of reconstructed images.However,these methods adopt mean square error as objective function to obtain a high evaluation index.As a result,they are unable to characterize good edge details,thereby failing to sufficiently infer plausible high frequency.To address this problem,we propose a novel generative adversarial network(GAN)for image superresolution combining perceptual loss to further improve SR performance.This method outperforms state-of-the-art methods by a large margin in terms of peak signal-to-noise ratio and structure similarity,resulting in noticeable improvement of the reconstruction results.Method SISR is inherently ill-posed because many solutions exist for any given low-resolution pixel.In other words,it is an underdetermined inverse problem that does not have a unique solution.Classical methods constrain the solution space by mitigating the prior information of a natural-scene image,thereby leading to unsatisfactory color analysis and context accuracy results with real high-resolution images.With its strong feature representation ability,CNN outperforms conventional methods.However,these forward CNNs for super-resolution are a single-path model that limits their reconstructive performance because they attempt to optimize the mean square error(MSE)in a pixelwise manner between the super-resolved image and the ground truth.Measuring pixel-wise difference cannot capture perceptual semantic well.Therefore,we propose a novel GAN for image super-resolution that integrates perceptual loss to boost visual performance.Our algorithm model c
作者
杨娟
李文静
汪荣贵
薛丽霞
Yang Juan;Li Wenjing;Wang Ronggui;Xue Lixia(School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China)
出处
《中国图象图形学报》
CSCD
北大核心
2019年第8期1270-1282,共13页
Journal of Image and Graphics
关键词
超分辨重建
深度学习
卷积神经网络
残差学习
生成对抗网络
感知损失
super-resolution reconstruction
deep learning
convolutional neural network(CNN)
residual learning
generative adversarial network(GAN)
perceptual loss
