Xiaoming-Yu/DMIT
Multi-mapping Image-to-Image Translation via Learning Disentanglement. NeurIPS2019
This tool helps researchers and computer vision engineers transform images from one style or domain to another, like changing a summer landscape to winter, or generating realistic images from semantic layouts. You provide a set of input images, and it generates diverse sets of corresponding output images that maintain key content but adopt a different visual characteristic. It's for those working with visual data who need flexible image manipulation capabilities.
113 stars. No commits in the last 6 months.
Use this if you need to translate images between different visual styles or conditions, such as adapting scene appearance or synthesizing objects based on descriptive inputs.
Not ideal if you're looking for a simple photo editor or a tool that performs pixel-level image enhancements without changing the overall domain or style.
Stars
113
Forks
17
Language
Python
License
MIT
Category
Last pushed
Jan 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Xiaoming-Yu/DMIT"
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