NVlabs/CenterPose

Single-Stage Keypoint-based Category-level Object Pose Estimation from an RGB Image (ICRA 2022)

43
/ 100
Emerging

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.

robotics augmented-reality computer-vision industrial-automation 3D-object-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

334

Forks

38

Language

Python

License

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.