Related papers: IEGAN: Multi-purpose Perceptual Quality Image Enha…

Since the advent of generative adversarial networks (GANs), various loss functions have been developed and combined to constitute the overall training objective function, in order to improve model performance or for specific learning tasks.…

Real low-resolution (LR) face images contain degradations which are too varied and complex to be captured by known downsampling kernels and signal-independent noises. So, in order to successfully super-resolve real faces, a method needs to…

In this paper, a novel strategy of Secure Steganograpy based on Generative Adversarial Networks is proposed to generate suitable and secure covers for steganography. The proposed architecture has one generative network, and two…

Novel photo-realistic texture synthesis is an important task for generating novel scenes, including asset generation for 3D simulations. However, to date, these methods predominantly generate textured objects in 2D space. If we rely on 2D…

Positron emission tomography (PET) is a widely used, highly sensitive molecular imaging in clinical diagnosis. There is interest in reducing the radiation exposure from PET but also maintaining adequate image quality. Recent methods using…

Despite remarkable progress in image translation, the complex scene with multiple discrepant objects remains a challenging problem. The translated images have low fidelity and tiny objects in fewer details causing unsatisfactory performance…

In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative network, the AttnGAN can…

This paper presents a generative adversarial network (GAN) based approach for radar image enhancement. Although radar sensors remain robust for operations under adverse weather conditions, their application in autonomous vehicles (AVs) is…

Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking images of faces, scenery and even medical images. Unfortunately, they usually require large training datasets, which are often scarce in…

Generative adversarial networks (GANs) can synthesize high-quality (HQ) images, and GAN inversion is a technique that discovers how to invert given images back to latent space. While existing methods perform on StyleGAN inversion, they have…

Deep learning algorithms produces state-of-the-art results for different machine learning and computer vision tasks. To perform well on a given task, these algorithms require large dataset for training. However, deep learning algorithms…

This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although…

Generative Adversarial Networks (GANs) in supervised settings can generate photo-realistic corresponding output from low-definition input (SRGAN). Using the architecture presented in the SRGAN original paper [2], we explore how selecting a…

Low-light image enhancement is generally regarded as a challenging task in image processing, especially for the complex visual tasks at night or weakly illuminated. In order to reduce the blurs or noises on the low-light images, a large…

A photo captured with bokeh effect often means objects in focus are sharp while the out-of-focus areas are all blurred. DSLR can easily render this kind of effect naturally. However, due to the limitation of sensors, smartphones cannot…

Generative adversarial networks or GANs are a type of generative modeling framework. GANs involve a pair of neural networks engaged in a competition in iteratively creating fake data, indistinguishable from the real data. One notable…

Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR)…

Intrinsic Image Decomposition (IID) is a challenging inverse problem that seeks to decompose a natural image into its underlying intrinsic components such as albedo and shading. While recent image decomposition methods rely on…

There are many factors affecting visual face recognition, such as low resolution images, aging, illumination and pose variance, etc. One of the most important problem is low resolution face images which can result in bad performance on face…

Among the major remaining challenges for generative adversarial networks (GANs) is the capacity to synthesize globally and locally coherent images with object shapes and textures indistinguishable from real images. To target this issue we…