Unpaired High-Resolution and Scalable Style Transfer Using Generative Adversarial Networks

10/10/2018
by   Andrej Junginger, et al.
0

Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators, especially in settings of generative adversarial networks (GANs). One special application is the field of image domain translations. Here, the goal is to take an image with a certain style (e.g. a photography) and transform it into another one (e.g. a painting). If such a task is performed for unpaired training examples, the corresponding GAN setting is complex, the neural networks are large, and this leads to a high peak memory consumption during, both, training and evaluation phase. This sets a limit to the highest processable image size. We address this issue by the idea of not processing the whole image at once, but to train and evaluate the domain translation on the level of overlapping image subsamples. This new approach not only enables us to translate high-resolution images that otherwise cannot be processed by the neural network at once, but also allows us to work with comparably small neural networks and with limited hardware resources. Additionally, the number of images required for the training process is significantly reduced. We present high-quality results on images with a total resolution of up to over 50 megapixels and emonstrate that our method helps to preserve local image details while it also keeps global consistency.

READ FULL TEXT
research
01/30/2021

Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks

We apply generative adversarial convolutional neural networks to the pro...
research
10/22/2022

Efficient Hair Style Transfer with Generative Adversarial Networks

Despite the recent success of image generation and style transfer with G...
research
10/08/2021

Collaging Class-specific GANs for Semantic Image Synthesis

We propose a new approach for high resolution semantic image synthesis. ...
research
07/08/2022

On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks

Spectrogram classification plays an important role in analyzing gravitat...
research
06/03/2019

Perceptual Embedding Consistency for Seamless Reconstruction of Tilewise Style Transfer

Style transfer is a field with growing interest and use cases in deep le...
research
11/19/2020

Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?

Generative Adversarial Networks (GANs) with style-based generators (e.g....
research
05/14/2019

Streetscape augmentation using generative adversarial networks: insights related to health and wellbeing

Deep learning using neural networks has provided advances in image style...

Please sign up or login with your details

Forgot password? Click here to reset