yhlleo/TriangleGAN
TriangleGAN, ACM MM 2019.
This project helps researchers and developers working with human-computer interaction or virtual reality create new hand gesture videos from existing ones. By taking a video of a person performing a gesture, it can generate a new video showing that same person performing a different target gesture, even if they haven't performed it before. It is ideal for those who need to synthesize diverse gesture data for training or evaluating gesture recognition systems.
No commits in the last 6 months.
Use this if you need to translate one hand gesture into another, generating realistic video sequences for applications like virtual avatars or interactive interfaces.
Not ideal if you are looking to animate full human body movements or require highly detailed facial expressions rather than hand gestures.
Stars
28
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yhlleo/TriangleGAN"
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