Corpus ID: 29630552

Face Super-Resolution Through Wasserstein GANs

  title={Face Super-Resolution Through Wasserstein GANs},
  author={Zhimin Chen and Yuguang Tong},
Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train. Recently, a series of papers (Arjovsky & Bottou, 2017a; Arjovsky et al. 2017b; and Gulrajani et al. 2017) proposed using Wasserstein distance as the training objective and promised easy, stable GAN training across architectures with minimal hyperparameter tuning… Expand
SRWGANTV: Image Super-Resolution Through Wasserstein Generative Adversarial Networks with Total Variational Regularization
  • Jun Shao, Liang Chen, Yi Wu
  • 2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)
  • 2021
The study of generative adversarial networks (GAN) has enormously promoted the research work on single image super-resolution (SISR) problem. SRGAN firstly apply GAN to SISR reconstruction, which hasExpand
HypervolGAN: An efficient approach for GAN with multi-objective training function
The proposed HypervolGAN adopts an adapted version of hypervolume maximization method to effectively define the multi-objective training function for GAN, and explores the integration of adversarial learning and optimization techniques, which can benefit not only image processing but also a wide range of applications. Expand
Nonlinear Multi-scale Super-resolution Using Deep Learning
A deep learning architecture capable of performing up to 8× single image super-resolution and employing Wasserstein GANs (WGANs) during training is proposed, which can recover small objects in satellite images during super- resolution whereas previous methods cannot. Expand
Improved face super-resolution generative adversarial networks
This paper decides to employ dense convolutional network blocks (dense blocks), which connect each layer to every other layer in a feed-forward fashion as the core of the very deep generator network G. Expand
Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
A simple yet effective structure of a multi-branch discriminator for enhancing an arbitrary generative adversarial architecture (GAN), named GAN-MBD, that takes advantage of the boosting strategy to break a common discriminator into several smaller ones with fewer parameters. Expand
Tiny face hallucination via boundary equilibrium generative adversarial networks
This paper works on tiny faces of size 16×16 pixels and magnifies them into their 8× upsampling ones by exploiting the boundary equilibrium generative adverarial networks (BEGAN). Expand
Multimodal-Boost: Multimodal Medical Image Super-Resolution using Multi-Attention Network with Wavelet Transform
This work proposes generative adversarial network (GAN) with deep multi-attention modules to learn high-frequency information from low-frequency data and presents a learning technique for training a domain-specific classifier as a perceptual loss function. Expand
Data Preprocessing for Soft Sensor Using Generative Adversarial Networks
  • Xiao Wang
  • Computer Science
  • 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)
  • 2018
A generative model named DWGAN based on improved Wasserstein generative adversarial networks (WGAN) is proposed to generate new samples for soft sensors, and experimental results show that the samples yielded by the proposed method behave more similarly with the real samples compared to samples provided by other methods. Expand
Data supplement for a soft sensor using a new generative model based on a variational autoencoder and Wasserstein GAN
The VA-WGAN combining VAE with Wasserstein generative adversarial networks (WGAN) as a generative model is established to produce new samples for soft sensors by using the decoder of VAE as the generator in WGAN. Expand
Artist Style Transfer Via Quadratic Potential
In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph. We train our neural networks in adversarial setting viaExpand


Improved Training of Wasserstein GANs
This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning. Expand
NIPS 2016 Tutorial: Generative Adversarial Networks
This report summarizes the tutorial presented by the author at NIPS 2016 on generative adversarial networks (GANs), and describes state-of-the-art image models that combine GANs with other methods. Expand
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
It is shown that certain IRL methods are in fact mathematically equivalent to GANs, and an equivalence between a sample-based algorithm for maximum entropy IRL and a GAN in which the generator's density can be evaluated and is provided as an additional input to the discriminator. Expand
Generative Adversarial Text to Image Synthesis
A novel deep architecture and GAN formulation is developed to effectively bridge advances in text and image modeling, translating visual concepts from characters to pixels. Expand
Image-to-Image Translation with Conditional Adversarial Networks
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Expand
Towards Principled Methods for Training Generative Adversarial Networks
The goal of this paper is to make theoretical steps towards fully understanding the training dynamics of generative adversarial networks, and performs targeted experiments to substantiate the theoretical analysis and verify assumptions, illustrate claims, and quantify the phenomena. Expand
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
This paper proposes Stacked Generative Adversarial Networks (StackGAN) to generate 256 photo-realistic images conditioned on text descriptions and introduces a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold. Expand
Generative Visual Manipulation on the Natural Image Manifold
This paper proposes to learn the natural image manifold directly from data using a generative adversarial neural network, and defines a class of image editing operations, and constrain their output to lie on that learned manifold at all times. Expand
On distinguishability criteria for estimating generative models
It is shown that a variant of NCE, with a dynamic generator network, is equivalent to maximum likelihood estimation, and that the key next step in GAN research is to determine whether GANs converge, and if not, to modify their training algorithm to force convergence. Expand
Deep Learning Face Attributes in the Wild
A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently. Expand