PangzeCheung/Dual-task-Pose-Transformer-Network
[CVPR 2022] Exploring Dual-task Correlation for Pose Guided Person Image Generation
This project helps fashion designers, e-commerce marketers, or virtual try-on developers transform a person's image from one pose to another. You provide an original image of a person and a target pose, and it generates a new image of that person in the desired pose, maintaining realistic clothing textures and details. This allows for creating diverse visual content without new photoshoots.
No commits in the last 6 months.
Use this if you need to generate high-quality images of people in different poses from a single source image, particularly for applications like virtual try-on or fashion catalog generation.
Not ideal if you need to manipulate facial expressions, change clothing items, or generate entirely new people, as it focuses specifically on pose transformation while preserving identity and garments.
Stars
98
Forks
12
Language
Python
License
—
Category
Last pushed
Apr 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PangzeCheung/Dual-task-Pose-Transformer-Network"
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