rludlow/3d-pose-2d-keypoints
3d Human Pose Estimation from 2d Keypoints
This project helps animators, game developers, or filmmakers convert 2D representations of human movement into realistic 3D poses. You provide 2D keypoints (like those indicating joints or limbs) from an image or video, and it outputs an estimated 3D skeletal pose. This is useful for anyone working with motion capture data who needs to reconstruct complex human movements in a 3D environment.
No commits in the last 6 months.
Use this if you need to accurately convert 2D human pose data into a 3D skeletal representation for animation, virtual reality, or biomechanical analysis.
Not ideal if your primary goal is real-time processing on embedded devices or if you require direct manipulation of raw video footage without prior keypoint extraction.
Stars
77
Forks
13
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 24, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rludlow/3d-pose-2d-keypoints"
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"