Related papers: Inpainting via Generative Adversarial Networks for…

We propose a GAN-based image compression method working at extremely low bitrates below 0.1bpp. Most existing learned image compression methods suffer from blur at extremely low bitrates. Although GAN can help to reconstruct sharp images,…

Generative Adversarial Networks (GANs) have recently demonstrated to successfully approximate complex data distributions. A relevant extension of this model is conditional GANs (cGANs), where the introduction of external information allows…

To efficiently extract textual information from color degraded document images is a significant research area. The prolonged imperfect preservation of ancient documents has led to various types of degradation, such as page staining, paper…

Generative adversarial networks (GANs) have been recently applied as a novel emulation technique for large scale structure simulations. Recent results show that GANs can be used as a fast, efficient and computationally cheap emulator for…

Reliable extraction of cosmological information from observed cosmic microwave background (CMB) maps may require removal of strongly foreground contaminated regions from the analysis. In this article, we employ an artificial neural network…

Semantic inpainting or image completion alludes to the task of inferring arbitrary large missing regions in images based on image semantics. Since the prediction of image pixels requires an indication of high-level context, this makes it…

Foreground masking and incomplete sky coverage complicate CMB polarization analyses by inducing mode coupling and imperfect E/B separation, with particularly strong impact on searches for primordial $B$-modes. We present SkyReconNet-P, a…

Prior knowledge of face shape and structure plays an important role in face inpainting. However, traditional face inpainting methods mainly focus on the generated image resolution of the missing portion without consideration of the special…

Image inpainting is one of the most challenging tasks in computer vision. Recently, generative-based image inpainting methods have been shown to produce visually plausible images. However, they still have difficulties to generate the…

An incomplete sky coverage poses difficulties in the extraction of the weak lensing information from the CMB. We test the reconstruction of the weak lensing convergence from CMB maps to which masks of point sources have been applied. We use…

Based on realistic simulations, we propose an hybrid method to reconstruct the lensing potential power spectrum, directly on PLANCK-like CMB frequency maps. It implies using a large galactic mask and dealing with a strong inhomogeneous…

The challenging task of image outpainting (extrapolation) has received comparatively little attention in relation to its cousin, image inpainting (completion). Accordingly, we present a deep learning approach based on Iizuka et al. for…

We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding…

Convolutional Neural Networks (CNNs) can play a key role in Medical Image Analysis under large-scale annotated datasets. However, preparing such massive dataset is demanding. In this context, Generative Adversarial Networks (GANs) can…

Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless…

The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. But this type of method generally attempts to generate one single "optimal" result, ignoring…

Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images. However, they often struggle in learning complex underlying modalities in a given dataset, resulting in poor-quality generated…

We consider inpainting in an unsupervised setting where there is neither access to paired nor unpaired training data. The only available information is provided by the uncomplete observations and the inpainting process statistics. In this…

Generative adversarial nets (GANs) have become a preferred tool for tasks involving complicated distributions. To stabilise the training and reduce the mode collapse of GANs, one of their main variants employs the integral probability…

We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual interpretations of a Convolutional Neural Network (CNN). To comprehend a CNN, the GAN is trained with information on how the CNN…