eslambakr/LAR-Look-Around-and-Refer

This is the official implementation for our paper;"LAR:Look Around and Refer".

29
/ 100
Experimental

This project helps computer vision researchers and developers improve how AI systems identify specific objects within complex 3D environments, based on natural language descriptions. It takes a 3D scene (like a room scan) and a text description as input, then outputs the precisely located 3D object that matches the description. This is useful for anyone building AI assistants, robotics, or spatial computing applications that need to understand and interact with objects in real-world 3D spaces.

No commits in the last 6 months.

Use this if you are working on 3D visual grounding tasks and want to enhance your model's accuracy by incorporating synthesized 2D image cues from 3D point clouds without needing actual 2D input images.

Not ideal if your primary focus is on 2D object recognition or if you require a simple, off-the-shelf solution without deep engagement in research-level computer vision.

3D-object-recognition spatial-computing robotics-perception AI-scene-understanding language-guided-identification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

30

Forks

2

Language

C++

License

MIT

Last pushed

Dec 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/eslambakr/LAR-Look-Around-and-Refer"

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