InternRobotics/Grounded_3D-LLM
Code&Data for Grounded 3D-LLM with Referent Tokens
This project helps researchers and developers working with 3D scenes to train a single model that can understand and respond to natural language queries about those scenes. It takes in 3D scan data and associated text descriptions, and outputs a model capable of tasks like answering questions about objects in a 3D space, generating descriptions, and identifying specific objects referenced in text. This is designed for AI/ML researchers, computer vision engineers, and developers building applications that require deep comprehension of 3D environments.
134 stars. No commits in the last 6 months.
Use this if you need to build a unified system for various 3D visual tasks, allowing you to interact with 3D scene data using natural language prompts rather than specialized models for each task.
Not ideal if you are looking for an out-of-the-box solution without significant technical setup or if your primary interest is in 2D image analysis rather than complex 3D scene understanding.
Stars
134
Forks
4
Language
Python
License
—
Category
Last pushed
Jan 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/InternRobotics/Grounded_3D-LLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice