SRGAN: Training Dataset Matters

by   Nao Takano, et al.

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].



page 3

page 5

page 6


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

Generating a novel image by manipulating two input images is an interest...

Iconify: Converting Photographs into Icons

In this paper, we tackle a challenging domain conversion task between ph...

A naive method to discover directions in the StyleGAN2 latent space

Several research groups have shown that Generative Adversarial Networks ...

toon2real: Translating Cartoon Images to Realistic Images

In terms of Image-to-image translation, Generative Adversarial Networks ...

Astronomical Image Colorization and upscaling with Generative Adversarial Networks

Automatic colorization of images without human intervention has been a s...

PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets

Deep learning architectures have enriched data analytics in the geoscien...

Words as Art Materials: Generating Paintings with Sequential GANs

Converting text descriptions into images using Generative Adversarial Ne...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.