Abstract Generative Adversarial Networks (GANs) have been widely used to generate
realistic-looking instances. However, training robust GAN is a non-trivial task due to the …

SAR images have the advantages of being less susceptible to clouds and light, while optical
images conform to the human vision system. Both of them are widely applied in the field of …

Deciphering oracle bone script is of great significance to the study of ancient Chinese
culture as well as archaeology. Although recent studies on oracle character recognition …

At present, most mainstream algorithms for single image super-resolution (SISR) assume
the image degradation process as an ideal degradation process (eg bicubic downscaling) …

Deep spatio-temporal neural networks have shown promising performance for video super-
resolution (VSR) in recent years. However, most of them heavily rely on accuracy motion …

This article presents an approach to significantly improve the resolution of a highly-sensitive
microwave planar sensor response with a super-resolution generative adversarial network …

We propose a new regularization method for deep learning based on the manifold
adversarial training (MAT). Unlike previous regularization and adversarial training methods …

Abstract Single Image Super Resolution (SISR) elevates spectral and spatial image
resolution beyond the sensor capabilities. Convolutional Neural Networks (CNNs) have …

Pose guided person image generation aims to transform a source person image to a target
pose. It is an ill-posed problem as we often need to generate pixels that are invisible in the …

Synthetic aperture radar (SAR) imagery has the advantages of all-day and all-weather
observation. However, due to the imaging mechanism of microwaves, it is difficult for …