nefeliandreou/PoseRepresentation
Official implementation of dual quaternion transformations as described in the paper "Pose Representations for Deep Skeletal Animation".
This project helps animation professionals and researchers work with complex skeletal motion data. It transforms raw motion capture (.bvh) files into various mathematical representations, including dual quaternions, to enable advanced deep learning techniques for animating characters. Animators, character riggers, and researchers in computer graphics who develop animation systems would find this valuable.
No commits in the last 6 months.
Use this if you need to convert skeletal animation data into different mathematical formats, particularly dual quaternions, for use in deep learning models or advanced character animation workflows.
Not ideal if you are looking for a ready-to-use animation tool or software for direct character animation, as this focuses on data representation for research and development.
Stars
35
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jul 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nefeliandreou/PoseRepresentation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"