lmb-freiburg/freihand
A dataset for estimation of hand pose and shape from single color images.
This project provides a comprehensive dataset to help computer vision researchers develop and train models that can accurately estimate human hand pose and shape from a single color image. It includes a vast collection of training and evaluation images of hands, complete with ground truth annotations for 3D hand joint positions and mesh shape. This is ideal for researchers in computer vision, robotics, or augmented reality who are working on hand tracking or gesture recognition systems.
430 stars. No commits in the last 6 months.
Use this if you are developing or evaluating deep learning models for precise 3D hand pose and shape estimation from standard camera images.
Not ideal if you need a dataset for real-time applications requiring multi-view calibration data or if you are not working within the academic research domain.
Stars
430
Forks
89
Language
Python
License
—
Category
Last pushed
Jan 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/lmb-freiburg/freihand"
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.