Ha0Tang/GestureGAN
[ACM MM 2018 Oral] GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
This tool helps researchers and developers working with computer vision to translate images from one hand gesture to another, or even change the viewpoint of an entire scene. You input an image of a person and some hand skeleton data, and it generates a new image of the same person with a different hand gesture. Alternatively, you can input an image of a scene and new semantic maps to generate the same scene from a different perspective.
176 stars. No commits in the last 6 months.
Use this if you need to generate synthetic image data for training computer vision models that recognize hand gestures or understand scene geometry from different viewpoints.
Not ideal if you require real-time image generation for interactive applications or if you are not comfortable with advanced machine learning setup and dataset preparation.
Stars
176
Forks
20
Language
Python
License
—
Category
Last pushed
Feb 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Ha0Tang/GestureGAN"
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