DuncanZauss/Keypoint_Communities
[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".
This project helps computer vision practitioners analyze human and object movements by identifying specific points (keypoints) on bodies and objects in images and videos. You provide an image or video, and it outputs a detailed 'pose' for each detected human or car, showing precise locations of joints, facial features, hands, feet, or car parts. This is useful for researchers and developers working on applications like sports analytics, autonomous driving, or human-computer interaction.
269 stars. No commits in the last 6 months.
Use this if you need to precisely track and analyze detailed poses of humans (including faces, hands, and feet) or cars in images or video streams.
Not ideal if you only need basic object detection or general image classification rather than fine-grained keypoint localization.
Stars
269
Forks
17
Language
Python
License
MIT
Category
Last pushed
Sep 30, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DuncanZauss/Keypoint_Communities"
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.