fraunhoferhhi/casapose

CASAPose: Class-Adaptive and Semantic-Aware Multi-Object Pose Estimation (BMVC 2022)

28
/ 100
Experimental

This project helps industrial engineers, robotics developers, and quality control professionals accurately determine the 3D position and orientation of multiple objects in an image. You provide it with images containing various objects and 3D models of those objects, and it outputs their precise poses. This is ideal for scenarios where machines or systems need to understand the exact location and rotation of physical items.

No commits in the last 6 months.

Use this if you need to precisely locate and orient multiple known objects from camera images, such as for robotic manipulation or automated inspection.

Not ideal if you need to identify objects that are not represented by a known 3D model, or if you only need 2D detection without depth and rotation information.

robotics industrial automation quality control machine vision pose estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

41

Forks

2

Language

Python

License

Last pushed

Nov 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/fraunhoferhhi/casapose"

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