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
Thermal Face Recognition Based on Multi-scale Image Synthesis
Wei-Ta Chu,Ping Shen Huang +1 more
TL;DR: In this article, a transformation-based method was proposed to achieve thermal face recognition, which is built on the basis of a generative adversarial network, mainly with the ideas of multi-scale discrimination and various loss functions like feature embedding, identity preservation and facial landmark-guided texture synthesis.
Proceedings ArticleDOI
An Approach to Super-Resolution of Sentinel-2 Images Based on Generative Adversarial Networks
TL;DR: A generative adversarial network based super-resolution (SR) approach to enhance the spatial resolution of Sentinel-2 spectral bands by utilizing the convolutional layers with residual connections and a long skip-connection between inputs and outputs is presented.
Journal ArticleDOI
Cali-sketch: Stroke calibration and completion for high-quality face image generation from human-like sketches
TL;DR: Cali-Sketch is proposed, a human-like-sketch to photo-realistic-image generation method that decouple a difficult cross-domain translation problem into two easier steps and is compared with state-of-the-art methods.
Posted Content
S2A: Wasserstein GAN with Spatio-Spectral Laplacian Attention for Multi-Spectral Band Synthesis
TL;DR: This study intends to address synthesis of high resolution multi-spectral satellite imagery using adversarial learning through spatio-spectrals Laplacian attention, and introduces a new cost function for the discriminator based on spatial attention and domain adaptation loss.
Proceedings ArticleDOI
Deep Progressive Convolutional Neural Network for Blind Super-Resolution With Multiple Degradations
TL;DR: A deep progressive network under a probabilistic framework and a novel up-sampling method for blind super-resolution with multiple degradations, which effectively utilizes image priors across scales are proposed.
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.