crockwell/rel_pose

[3DV 2022] The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs

34
/ 100
Emerging

This project helps computer vision engineers and robotics researchers determine the precise spatial relationship between two camera views. By analyzing a pair of images, it outputs the relative orientation and position (pose) of one camera concerning the other. This is particularly useful for tasks like 3D reconstruction, augmented reality, or robot navigation where understanding camera movement is crucial.

No commits in the last 6 months.

Use this if you need to accurately estimate the relative camera pose from image pairs, especially for applications like robotic mapping, virtual reality scene understanding, or 3D modeling where visual features alone aren't enough.

Not ideal if you are looking for a simple, out-of-the-box solution that doesn't require significant setup with datasets and environment configurations, or if your application doesn't involve computer vision or robotics.

robotics 3D-reconstruction computer-vision SLAM augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

96

Forks

6

Language

Python

License

BSD-3-Clause

Last pushed

Jan 17, 2023

Commits (30d)

0

Get this data via API

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

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