InternRobotics/PointLLM

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

35
/ 100
Emerging

This project offers a specialized Large Language Model (LLM) designed to interpret 3D object data. You input raw 3D point clouds, and the model understands the object's type, shape, and appearance, producing descriptive text. This is for researchers and engineers working with 3D sensor data who need to automatically describe or classify objects.

983 stars. No commits in the last 6 months.

Use this if you need an AI model that can understand and generate descriptions directly from 3D point cloud data, without being confused by depth ambiguities or occlusions.

Not ideal if your primary data source is 2D images or videos, or if you don't work with raw 3D point cloud representations.

3D-object-recognition point-cloud-analysis robotics-perception computer-vision autonomous-systems
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

983

Forks

53

Language

Python

License

Last pushed

Aug 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/InternRobotics/PointLLM"

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