ai4ce/MSG

[NeurIPS2024] Multiview Scene Graph (topologically representing a scene from unposed images by interconnected place and object nodes)

31
/ 100
Emerging

This project helps roboticists and autonomous system developers understand and represent complex environments from multiple unposed images. It takes a collection of images of a scene and creates a 'scene graph' that describes the objects within the scene and their relationships, along with their locations. This allows for applications like robot navigation and scene reconstruction.

126 stars. No commits in the last 6 months.

Use this if you need to build a structured, topological understanding of an environment from diverse image inputs, especially for robotics or augmented reality applications.

Not ideal if your primary goal is simple object detection or image classification without the need for spatial relationships or scene topology.

robotics autonomous-navigation spatial-mapping computer-vision augmented-reality
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

126

Forks

9

Language

Python

License

Last pushed

Sep 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ai4ce/MSG"

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