cohyun / poseviz

3D Human Pose Visualizer for Python

PoseViz – 3D Human Pose Visualizer

Multi-person, multi-camera 3D human pose visualization tool built using Mayavi. As used in MeTRAbs visualizations.

This repo does not contain pose estimation code, only the visualization part.

Gist of Usage

import poseviz

viz = poseviz.PoseViz(...)
camera = poseviz.Camera(...)
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.

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

PoseViz is released as a conda package (experimental, tested only on Linux):

conda install poseviz -c isarandi

Alternatively, in case the above doesn't work, install Mayavi via conda (the Mayavi pip package has compilation problems), clone this repo and install PoseViz via pip:

conda install mayavi -c conda-forge
pip install git+https://github.com/isarandi/poseviz.git

Then run demo.py to test if installation was successful.