https://github.com/isarandi/poseviz
3D Human Pose Visualizer for Python
https://github.com/isarandi/poseviz
3d-human-pose 3d-viewer 3d-visualization mayavi pose-estimation python
Last synced: 3 months ago
JSON representation
3D Human Pose Visualizer for Python
- Host: GitHub
- URL: https://github.com/isarandi/poseviz
- Owner: isarandi
- License: mit
- Created: 2021-10-18T18:28:08.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2026-03-21T11:33:44.000Z (3 months ago)
- Last Synced: 2026-03-22T02:46:57.002Z (3 months ago)
- Topics: 3d-human-pose, 3d-viewer, 3d-visualization, mayavi, pose-estimation, python
- Language: Python
- Homepage:
- Size: 769 KB
- Stars: 167
- Watchers: 6
- Forks: 18
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# PoseViz – 3D Human Pose and Mesh Visualizer
Multi-person, multi-camera 3D human pose and mesh visualization tool built using
OpenGL (via ModernGL). As used in [NLF](https://github.com/isarandi/nlf) and [MeTRAbs](https://github.com/isarandi/metrabs) visualizations.
**This repo does not contain pose estimation code, only the visualization part.**
## Gist of Usage
```python
import poseviz
import deltacamera
camera = deltacamera.Camera(...)
with poseviz.PoseViz(...) as viz:
for frame in frames:
bounding_boxes, poses3d = run_pose_estimation_model(frame)
viz.update(frame=frame, boxes=bounding_boxes, poses=poses3d, camera=camera)
```
See also [```demo.py```](demo.py).
The main feature of this tool is that the graphical event loop is hidden from the library user. We
want to write code in terms of the *prediction loop* of the human pose estimator, not from the point
of view of the visualizer tool.
Behind the scenes, this is achieved through forking a dedicated visualization process and passing
new scene information via multiprocessing queues.
## Installation
```bash
pip install poseviz
```
Then run [demo.py](demo.py) to test if installation was successful.