NVlabs/CenterPose
Single-Stage Keypoint-based Category-level Object Pose Estimation from an RGB Image (ICRA 2022)
This project helps identify and track the precise 3D position and orientation of objects like bikes, bottles, or shoes in images or videos, even if they are unfamiliar instances of a known category. You input a standard RGB image or video, and it outputs the object's 3D pose, bounding box, and dimensions. This is ideal for roboticists, augmented reality developers, or industrial automation engineers needing to understand an object's spatial properties.
334 stars. No commits in the last 6 months.
Use this if you need to accurately determine the 3D position and orientation (pose) of various objects from a single camera view, especially for robotics or AR applications.
Not ideal if you only need 2D object detection or if your application requires identifying objects outside of the nine pre-trained categories (bike, book, bottle, camera, cereal_box, chair, cup, laptop, and shoe) without custom training.
Stars
334
Forks
38
Language
Python
License
—
Category
Last pushed
Sep 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVlabs/CenterPose"
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.