NilouAp/StyleGAN_for_Face_Frontalization
Identity-Preserving Face Frontalization with StyleGAN on CMU Multi-PIE
This project helps improve facial recognition system accuracy by converting non-frontal face images into clear, front-facing views. It takes a profile or angled image of a face and outputs a new image showing the same person looking directly ahead, while ensuring their identity is perfectly preserved. This is for professionals working with facial recognition, security, or identity verification systems.
No commits in the last 6 months.
Use this if you need to standardize facial images to a frontal pose for improved accuracy in existing facial recognition systems or identity verification workflows.
Not ideal if you need to process faces for artistic purposes, general image editing, or if your primary goal is not identity preservation for recognition.
Stars
16
Forks
—
Language
Python
License
MIT
Category
Last pushed
Dec 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NilouAp/StyleGAN_for_Face_Frontalization"
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