ilovepose/DarkPose
Distribution-Aware Coordinate Representation for Human Pose Estimation
This project helps improve the accuracy of human pose estimation from images or videos. It takes existing pose estimation models and an input image, then produces more precise predictions of key body points, like elbows, knees, or wrists. It's used by researchers and engineers building systems that need highly accurate tracking of human movement.
565 stars. No commits in the last 6 months.
Use this if you are developing computer vision applications that require highly accurate human pose tracking from images or video.
Not ideal if you need a complete, end-to-end human pose estimation solution without integrating it with other models.
Stars
565
Forks
82
Language
Cuda
License
Apache-2.0
Category
Last pushed
May 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ilovepose/DarkPose"
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.