KyungMinJin/HANet
Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos (WACV 2023)
This project helps researchers and engineers accurately track human movement in videos. It takes video footage as input and outputs precise 2D and 3D human pose estimations, including body mesh recovery, even with occlusions or rapid motion. This is for computer vision researchers, biomechanists, and animators who need high-quality human motion data.
No commits in the last 6 months.
Use this if you need to analyze detailed human kinematics from video, such as for sports analysis, medical diagnostics, or creating realistic character animations.
Not ideal if you are looking for a plug-and-play application without needing to run experiments or work with machine learning frameworks.
Stars
54
Forks
4
Language
Python
License
—
Category
Last pushed
Oct 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/KyungMinJin/HANet"
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.