GengDavid/pytorch-cpn
A PyTorch re-implementation of CPN (Cascaded Pyramid Network for Multi-Person Pose Estimation)
This project helps computer vision researchers and developers accurately identify human body joints in images, even when multiple people are present or partially obscured. You input images containing people, and it outputs precise coordinates for key body points like elbows, knees, and shoulders. This is useful for anyone working on human motion analysis, activity recognition, or creating interactive experiences.
499 stars. No commits in the last 6 months.
Use this if you need to reliably detect and track human poses in still images or video frames for research or application development.
Not ideal if you're looking for a drag-and-drop tool for immediate end-user applications without any coding or integration.
Stars
499
Forks
97
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 21, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/GengDavid/pytorch-cpn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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.