tamasino52/U-CondDGCN
Unofficial pytorch implementation of U-CondDGCN from "WenBo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, Tien-Tsin Wong : Conditional Directed Graph Convolution for 3D Human Pose Estimation"
This project helps researchers and engineers accurately determine 3D human body poses from standard 2D video footage. It takes a video of a person as input and outputs a precise 3D representation of their skeleton and joint positions. This is primarily useful for academics and computer vision practitioners working on human motion analysis.
No commits in the last 6 months.
Use this if you need to translate 2D video data into highly accurate 3D skeletal poses for analysis or further processing.
Not ideal if you need a real-time, lightweight solution for mobile devices or embedded systems, or if your primary input is not video.
Stars
46
Forks
7
Language
Python
License
MIT
Category
Last pushed
Dec 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tamasino52/U-CondDGCN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
UPC-ViRVIG/SparsePoser
Official Code for ACM Transactions on Graphics (TOG) paper "SparsePoser: Real-time Full-body...
Silverster98/HUMANISE
Official implementation of the NeurIPS22 paper "HUMANISE: Language-conditioned Human Motion...
syguan96/DynaBOA
[T-PAMI 2022] Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation