Astronomical Image Colorization and upscaling with Generative Adversarial Networks

12/27/2021
by   Shreyas Kalvankar, et al.
2

Automatic colorization of images without human intervention has been a subject of interest in the machine learning community for a brief period of time. Assigning color to an image is a highly ill-posed problem because of its innate nature of possessing very high degrees of freedom; given an image, there is often no single color-combination that is correct. Besides colorization, another problem in reconstruction of images is Single Image Super Resolution, which aims at transforming low resolution images to a higher resolution. This research aims to provide an automated approach for the problem by focusing on a very specific domain of images, namely astronomical images, and process them using Generative Adversarial Networks (GANs). We explore the usage of various models in two different color spaces, RGB and L*a*b. We use transferred learning owing to a small data set, using pre-trained ResNet-18 as a backbone, i.e. encoder for the U-net and fine-tune it further. The model produces visually appealing images which hallucinate high resolution, colorized data in these results which does not exist in the original image. We present our results by evaluating the GANs quantitatively using distance metrics such as L1 distance and L2 distance in each of the color spaces across all channels to provide a comparative analysis. We use Frechet inception distance (FID) to compare the distribution of the generated images with the distribution of the real image to assess the model's performance.

READ FULL TEXT

page 2

page 5

page 9

page 11

research
04/28/2022

Generative Adversarial Networks for Image Super-Resolution: A Survey

Single image super-resolution (SISR) has played an important role in the...
research
01/21/2020

Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques

Single Image Super-Resolution (SISR) task refers to learn a mapping from...
research
03/14/2018

Image Colorization with Generative Adversarial Networks

Over the last decade, the process of automatic colorization had been stu...
research
10/13/2017

Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolution

We propose an image super resolution(ISR) method using generative advers...
research
07/08/2020

Words as Art Materials: Generating Paintings with Sequential GANs

Converting text descriptions into images using Generative Adversarial Ne...
research
06/21/2017

cGAN-based Manga Colorization Using a Single Training Image

The Japanese comic format known as Manga is popular all over the world. ...
research
03/24/2019

SRGAN: Training Dataset Matters

Generative Adversarial Networks (GANs) in supervised settings can genera...

Please sign up or login with your details

Forgot password? Click here to reset