Ha0Tang/AsymmetricGAN
[ACCV 2018 Oral] Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
This project helps visual content creators and researchers by transforming an input image based on desired structural changes. You provide an original image and a 'control' image or skeleton showing the new pose or viewpoint. The system then generates a new image of the same person or scene, but with the specified new gesture or perspective. It's ideal for anyone needing to generate variations of existing images without manual editing.
No commits in the last 6 months.
Use this if you need to create realistic image variations where a subject's pose or a scene's viewpoint is altered, especially for hand gestures or different camera angles.
Not ideal if you're looking for simple image filtering or basic edits like color correction, or if you don't have structured 'control' data to guide the image transformation.
Stars
45
Forks
6
Language
Python
License
—
Category
Last pushed
Jul 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Ha0Tang/AsymmetricGAN"
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