ponimatkin/focalpose

[CVPR 2022] Focal Length and Object Pose Estimation via Render and Compare

39
/ 100
Emerging

This project helps computer vision researchers and engineers accurately determine the orientation and distance (focal length) of objects in images. You provide an image containing an object and its class (e.g., "chair", "car"), and it outputs images with 3D models precisely aligned to the detected object, along with camera parameters. It is ideal for those developing systems that need to understand 3D object properties from 2D pictures.

No commits in the last 6 months.

Use this if you need to precisely estimate the 3D pose and focal length of objects in images, particularly for research or applications in robotics, augmented reality, or 3D scene understanding.

Not ideal if you're looking for a simple, out-of-the-box solution for general object detection or classification without needing detailed 3D pose information.

computer-vision 3d-object-pose-estimation augmented-reality-development robotics-perception scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

82

Forks

11

Language

Python

License

MIT

Last pushed

May 24, 2023

Commits (30d)

0

Get this data via API

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

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