Blade6570/Learningimage-to-imagetranslationusingpairedandunpairedtrainingsamples
Learning image-to-image translation using paired and unpaired training samples
This project helps computer vision researchers and practitioners transform images from one domain to another. For example, it can convert satellite images into street maps or day-time photos into night-time scenes. It takes input images (either as pairs, like a photo and its segmented version, or unpaired images from two different styles) and generates corresponding images in the target domain.
No commits in the last 6 months.
Use this if you need to translate images from one visual representation to another, especially when you have a mix of paired and unpaired examples for training.
Not ideal if you are looking for an out-of-the-box application for general image editing or style transfer without a research or development focus.
Stars
20
Forks
3
Language
Python
License
—
Category
Last pushed
May 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Blade6570/Learningimage-to-imagetranslationusingpairedandunpairedtrainingsamples"
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)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017