SRGAN: Training Dataset Matters

03/24/2019
by   Nao Takano, et al.
0

Generative Adversarial Networks (GANs) in supervised settings can generate photo-realistic corresponding output from low-definition input (SRGAN). Using the architecture presented in the SRGAN original paper [2], we explore how selecting a dataset affects the outcome by using three different datasets to see that SRGAN fundamentally learns objects, with their shape, color, and texture, and redraws them in the output rather than merely attempting to sharpen edges. This is further underscored with our demonstration that once the network learns the images of the dataset, it can generate a photo-like image with even a slight hint of what it might look like for the original from a very blurry edged sketch. Given a set of inference images, the network trained with the same dataset results in a better outcome over the one trained with arbitrary set of images, and we report its significance numerically with Frechet Inception Distance score [22].

READ FULL TEXT

page 3

page 5

page 6

research
12/09/2022

Album cover art image generation with Generative Adversarial Networks

Generative Adversarial Networks (GANs) were introduced by Goodfellow in ...
research
04/07/2020

Iconify: Converting Photographs into Icons

In this paper, we tackle a challenging domain conversion task between ph...
research
04/20/2018

Generating a Fusion Image: One's Identity and Another's Shape

Generating a novel image by manipulating two input images is an interest...
research
03/19/2022

A naive method to discover directions in the StyleGAN2 latent space

Several research groups have shown that Generative Adversarial Networks ...
research
11/13/2020

Fast and Scalable Earth Texture Synthesis using Spatially Assembled Generative Adversarial Neural Networks

The earth texture with complex morphological geometry and compositions s...
research
12/27/2021

Astronomical Image Colorization and upscaling with Generative Adversarial Networks

Automatic colorization of images without human intervention has been a s...
research
01/26/2020

Using Simulated Data to Generate Images of Climate Change

Generative adversarial networks (GANs) used in domain adaptation tasks h...

Please sign up or login with your details

Forgot password? Click here to reset