当前位置: X-MOL 学术Mach. Vis. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
RSRGAN: computationally efficient real-world single image super-resolution using generative adversarial network
Machine Vision and Applications ( IF 3.3 ) Pub Date : 2020-10-08 , DOI: 10.1007/s00138-020-01135-9
Vishal Chudasama , Kishor Upla

Recently, convolutional neural network has been employed to obtain better performance in single image super-resolution task. Most of these models are trained and evaluated on synthetic datasets in which low-resolution images are synthesized with known bicubic degradation and hence they perform poorly on real-world images. However, by stacking more convolution layers, the super-resolution (SR) performance can be improved. But, such idea increases the number of training parameters and it offers a heavy computational burden on resources which makes them unsuitable for real-world applications. To solve this problem, we propose a computationally efficient real-world image SR network referred as RSRN. The RSRN model is optimized using pixel-wise \(L_1\) loss function which produces overly-smooth blurry images. Hence, to recover the perceptual quality of SR image, a real-world image SR using generative adversarial network called RSRGAN is proposed. Generative adversarial network has an ability to generate perceptual plausible solutions. Several experiments have been conducted to validate the effectiveness of the proposed RSRGAN model, and it shows that the proposed RSRGAN generates SR samples with more high-frequency details and better perception quality than that of recently proposed SRGAN and \(\hbox {SRFeat}_{\textit{IF}}\) models, while it sets comparable performance with the ESRGAN model with significant less number of training parameters.



中文翻译:

RSRGAN:使用生成对抗网络计算高效的真实世界单图像超分辨率

最近,卷积神经网络已被用于在单图像超分辨率任务中获得更好的性能。这些模型中的大多数都是在合成数据集上进行训练和评估的,在合成数据集中,低分辨率图像以已知的三次立方分解而合成,因此它们在现实世界图像上的性能较差。但是,通过堆叠更多的卷积层,可以提高超分辨率(SR)性能。但是,这样的想法增加了训练参数的数量,并且给资源提供了沉重的计算负担,这使其不适合实际应用。为了解决此问题,我们提出了一种计算效率很高的真实世界图像SR网络,称为RSRN。使用像素级\(L_1 \)优化RSRN模型损失功能,产生过于平滑的模糊图像。因此,为了恢复SR图像的感知质量,提出了使用称为RSRGAN的生成对抗网络的真实世界图像SR。生成对抗网络具有生成感知上可行的解决方案的能力。已经进行了一些实验来验证所提出的RSRGAN模型的有效性,并且表明,与最近提出的SRGAN和\(\ hbox {SRFeat} _相比,所提出的RSRGAN生成的SR样本具有更多的高频细节和更好的感知质量。{\ textit {IF}} \)模型,同时使用较少的训练参数设置与ESRGAN模型可比的性能。

更新日期:2020-10-08
down
wechat
bug