sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
This tool helps you transform images from one visual style or domain to another, even when you don't have perfectly matched examples. For instance, you can convert drawings of edges into realistic shoes or handbags, change a person's hair color in a photo, or even transform a car's appearance to resemble a human face. It takes a collection of images from a 'source' domain and outputs corresponding images in a 'target' domain. This is useful for graphic designers, artists, or anyone working with visual content creation or style transfer.
195 stars. No commits in the last 6 months.
Use this if you need to translate images from one visual characteristic or domain to another without requiring exact paired examples.
Not ideal if you need pixel-perfect, highly accurate transformations where the input and output images must retain identical underlying structure, or if you are looking for a simple, ready-to-use application rather than a coding project.
Stars
195
Forks
39
Language
Python
License
—
Category
Last pushed
Apr 06, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sagiebenaim/DistanceGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
weihaox/awesome-image-translation
Collection of awesome resources on image-to-image translation.