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
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.
Stars
391
Forks
69
Language
MATLAB
License
MIT
Category
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.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.