wuhuikai/GP-GAN
A Chainer implementation of GP-GAN, a GAN-based algorithm for blending source and destination images into realistic high-resolution composites.
Not currently ranked — collecting fresh signals.
star history
This repository contains the official implementation of a deep generative model paper for image blending tasks. The algorithm takes a source image, destination image, and mask as input, then uses a Wasserstein GAN trained on blended images to produce photorealistic high-resolution composites. It was published as an oral presentation at ACMMM 2019.
Frequently asked
- What is wuhuikai/GP-GAN?
- A Chainer implementation of GP-GAN, a GAN-based algorithm for blending source and destination images into realistic high-resolution composites.
- Is GP-GAN open source?
- Yes — wuhuikai/GP-GAN is open source, released under the MIT license.
- What language is GP-GAN written in?
- wuhuikai/GP-GAN is primarily written in Python.
- How popular is GP-GAN?
- wuhuikai/GP-GAN has 472 stars on GitHub.
- Where can I find GP-GAN?
- wuhuikai/GP-GAN is on GitHub at https://github.com/wuhuikai/GP-GAN.