mks0601/V2V-PoseNet_RELEASE

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

48
/ 100
Emerging

This project helps researchers and developers accurately track the 3D movement and positioning of hands and human bodies using only a single depth sensor. It takes depth map images as input and provides precise 3D coordinates for key joints of the hand or body as output. This tool is ideal for computer vision engineers, robotics researchers, and anyone developing applications that require highly accurate real-time pose estimation from depth data.

391 stars. No commits in the last 6 months.

Use this if you need to precisely estimate 3D hand or human poses from individual depth images for research, prototyping, or integrating into specialized computer vision systems.

Not ideal if you need a pre-built application for general consumer use, a real-time system that uses standard RGB cameras, or a solution without significant technical setup.

3D hand tracking human pose estimation depth sensing computer vision research robotics perception
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

391

Forks

69

Language

MATLAB

License

MIT

Last pushed

Jul 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mks0601/V2V-PoseNet_RELEASE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.