Capturing ground truth data to benchmark super-resolution (SR) is challenging. Therefore,
current quantitative studies are mainly evaluated on simulated data artificially sampled from …

摘要针对目前卷积神经网络的超分辨率算法存在卷积层数少, 模型简单, 计算量大,
收敛速度慢以及图像纹理模糊等问题, 提出了一种基于深层残差网络的加速图像超分辨率重建 …

With constant advances in deep learning methods as applied to image processing, deep
convolutional neural networks (CNNs) have been widely explored in single‐image super …

Reconstruction of super-resolution CT images using deep learning requires a large number
of high-resolution images. However, high-resolution images are often limited to access due …

Aiming at the problems of the face image super-resolution reconstruction method based on
convolutional neural network, such as single feature extraction scale, low utilization rate of …

The super-resolution of depth images is a research hotspot. In this study, the classical
Kriging algorithm is applied to the spatial interpolation of depth images, together with the …

Aerial images are often applied into disaster area surveillance. High-resolution (HR) aerial
images are preferred to monitor the disaster area since they can provide abundant …

Low-quality medical ultrasound images have serious spots, noise, and weak borders
between similar tissues, which affect the accuracy of segmentation of human organs and …

A super-resolution enhancement algorithm was proposed based on the combination of
fractional calculus and Projection onto Convex Sets (POCS) for unmanned aerial vehicles …

针对极深神经网络图像超分辨率重建过程中, 存在图像特征提取少, 信息利用率低, 平等处理高,
低频信息通道的问题, 提出了残差卷积注意网络的图像超分辨率重建算法 …