cvg/nice-slam

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

48
/ 100
Emerging

This project helps robotics engineers and researchers create detailed 3D maps of indoor environments using video from a moving camera. It takes a sequence of color and depth images (RGB-D video) captured by a camera moving through a space and outputs an accurate, dense 3D mesh model of the scene and the camera's precise path. This is ideal for anyone developing autonomous robots or augmented reality applications that need to understand and navigate physical spaces.

1,569 stars. No commits in the last 6 months.

Use this if you need to generate highly accurate 3D maps and track camera movement simultaneously for indoor environments from RGB-D video input.

Not ideal if you are working with outdoor scenes, require real-time mapping on constrained hardware, or only have standard RGB video without depth information.

robotics augmented-reality 3D-reconstruction indoor-mapping computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,569

Forks

209

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cvg/nice-slam"

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