Single Image Super Image Resolution

Introduction

The task of super image resolution is of crucial importance. We are often faced with situations where in we are needed to work with high resolution images. However high resolution images are often expensive in terms of memory and computation. Super image resolution allows us to save time and money required to transport high resolution images and videos by taking low resolution images/videos and converting them to the desired high resolution.

The Problem Statement

Our objective is to take a low resolution image and produce an estimate of a corresponding high‑resolution image. Using deep learning and GAN models in order to convert a low resolution image to an image of the desired higher resolution is what we achieve to do in our current project.

Uses in real life

1. Surveillance: to detect, identify, and perform facial recognition on low-resolution images obtained from security cameras.
2. Medical: capturing high-resolution MRI images can be tricky when it comes to scan time, spatial coverage, and signal-to-noise ratio (SNR).    Super resolution helps resolve this by generating high-resolution MRI from otherwise low-resolution MRI images.
3. Media: super resolution can be used to reduce server costs, as media can be sent at a lower resolution and upscaled on the fly.

References

1. Image Super-Resolution Using Deep Convolutional Networks Chao Dong, Chen Change Loy, Member, IEEE, Kaiming He, Member, IEEE, and Xiaoou Tang, Fellow, IEEE
2. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang
3. https://github.com/SaoYan/DnCNN-PyTorch
4. https://github.com/tegg89/SRCNN-Tensorflow
5. Checkerboard artifact free sub-pixel convolution A note on sub-pixel convolution, resize convolution and convolution resize Andrew Aitken*, Christian Ledig*, Lucas Theis*, Jose Caballero, Zehan Wang, Wenzhe Shi* Twitter, Inc.
6. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network Wenzhe Shi1 , Jose Caballero1 , Ferenc Huszar´ 1 , Johannes Totz1 , Andrew P. Aitken1 , Rob Bishop1 , Daniel Rueckert1 , Zehan Wang1 (Twitter)
7. Generative Adversarial Nets Ian J. Goodfellow, Jean Pouget-Abadie∗ , Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair† , Aaron Courville, Yoshua Bengio‡ Departement d’informatique et de recherche op ´ erationnelle ´ Universite de Montr ´ eal ´ Montreal, QC H3C 3J7

Dataset Download

https://data.vision.ee.ethz.ch/cvl/DIV2K/