Open AccessPosted Content
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Xintao Wang,Ke Yu,Shixiang Wu,Jinjin Gu,Yihao Liu,Chao Dong,Chen Change Loy,Yu Qiao,Xiaoou Tang +8 more
Reads0
Chats0
TLDR
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.Abstract:
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge. The code is available at this https URL .read more
Citations
More filters
Book ChapterDOI
Human Brain Computer/Machine Interface System Feasibility Study for Independent Core Observer Model Based Artificial General Intelligence Collective Intelligence Systems
David J. Kelley,Kyrtin Atreides +1 more
TL;DR: This paper is primarily designed to help address the feasibility of building optimized mediation clients for the Independent Core Observer Model (ICOM) cognitive architecture for Artificial General Intelligence (AGI) mediated Artificial Super Intelligence (mASI) research program.
Journal ArticleDOI
Deep learning approaches to inverse problems in imaging: Past, present and future
TL;DR: In this paper, a review of deep learning and hybrid methods for image and video super-resolution and image restoration is presented, focusing on image inverse problems, and the challenges of applying deep learning models to solve them.
Journal ArticleDOI
Efficient Spatial Pyramid of Dilated Convolution and Bottleneck Network for Zero-Shot Super Resolution
TL;DR: A novel zero-shot learning (ZSL) network for super resolution with efficient spatial pyramid of dilated convolutions network with bottleneck (ESP-BNet) is applied in the model as an efficient computational structure to enhance the feature representation.
Journal ArticleDOI
Adaptive Diagonal Total-Variation Generative Adversarial Network for Super-Resolution Imaging
TL;DR: A novel model called the ADTV-SRGAN is designed based on the adaptive diagonal total-variation generative adversarial network to address problems that the loss function does not correlate well with perceptual vision in super-resolution methodsbased on the convolutional neural network.
Posted Content
Super-resolution of Omnidirectional Images Using Adversarial Learning
TL;DR: In this paper, an improved generative adversarial network based model was proposed to handle the artifacts obtained in the spherical observational space, which can improve the super-resolution at a fine scale.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.