nv-nguyen/template-pose

[CVPR 2022] Pytorch implementation of "Templates for 3D Object Pose Estimation Revisited: Generalization to New objects and Robustness to Occlusions" paper

30
/ 100
Emerging

This project helps industrial automation engineers or quality control specialists accurately determine the 3D position and orientation of physical objects from camera images. You input camera images of an object, along with its 3D CAD model, and the system outputs the precise 3D pose (position and rotation) of that object in the image. This is particularly useful for tasks like robotic grasping or assembly where objects may be partially hidden or new to the system.

189 stars. No commits in the last 6 months.

Use this if you need to precisely track the 3D pose of objects in industrial or robotic settings, especially when dealing with new objects or those that are partially obscured.

Not ideal if you are looking for a real-time, lightweight solution for simple 2D object detection or tracking without needing precise 3D pose information.

industrial-automation robotics quality-inspection computer-vision 3d-object-tracking
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

189

Forks

15

Language

Python

License

Last pushed

Dec 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/nv-nguyen/template-pose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.