Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

by   Christian Ledig, et al.

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.


page 2

page 8

page 13

page 15

page 16

page 17

page 18

page 19


IEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network

Despite the breakthroughs in quality of image enhancement, an end-to-end...

SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution

Single image super resolution (SISR) is to reconstruct a high resolution...

Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination

Recently, many convolutional neural networks for single image super-reso...

FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform

Single image super-resolution(SISR) is an ill-posed problem that aims to...

iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks

Recently, learning-based models have enhanced the performance of single-...

Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution

The traditional super-resolution methods that aim to minimize the mean s...

Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution

Single image super-resolution (SISR) is an ill-posed problem with an ind...

Code Repositories


A tensorflow implemenation of Christian et al's SRGAN(super-resolution generative adversarial network)

view repo


pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

view repo


A modern PyTorch implementation of SRGAN

view repo


Compressed Sensing MRI based on Deep Generative Adversarial Network

view repo



view repo