Super-Resolution

1473 papers with code • 1 benchmarks • 22 datasets

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Most implemented papers

Generative Adversarial Networks

goodfeli/adversarial Proceedings of the 27th International Conference on Neural Information Processing Systems 2014

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: 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. The training procedure for G is to maximize the probability of D making a mistake.

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

tensorflow/models CVPR 2017

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.

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

alexjc/neural-enhance 27 Mar 2016

We consider image transformation problems, where an input image is transformed into an output image.

Image Super-Resolution Using Deep Convolutional Networks

nagadomi/waifu2x 31 Dec 2014

We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.

Enhanced Deep Residual Networks for Single Image Super-Resolution

LimBee/NTIRE2017 10 Jul 2017

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN).

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

xinntao/ESRGAN 1 Sep 2018

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).

SinGAN: Learning a Generative Model from a Single Natural Image

tamarott/SinGAN ICCV 2019

We introduce SinGAN, an unconditional generative model that can be learned from a single natural image.

High-Resolution Image Synthesis with Latent Diffusion Models

compvis/stable-diffusion CVPR 2022

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

cszn/DnCNN 13 Aug 2016

Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.