Skip to content
프로젝트

Chuny1/3DGPT has 854 GitHub stars and 46 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-22 00:09 UTC. Last push 2025-03-05.

이 수치를 측정하는 방법

측정된 스타 증가

in 24h
0
in 7 days
0
in 15 days
기록 수집 중
in 1 month
기록 수집 중

서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.

소개

Chunyi Sun👩*, Junlin Han👱*, Weijian Deng👱, Xinlong Wang👱, Zishan Qin👩, Stephen Gould‍️👨‍🦱

개발 도구

README.md

Original

🏔️🤖 3D-GPT: Procedural 3D Modeling with Large Language Models

🏆 3DV Conference Paper Main Image

👥 Authors

Chunyi Sun👩*, Junlin Han👱*, Weijian Deng👱, Xinlong Wang👱, Zishan Qin👩, Stephen Gould‍️👨‍🦱

🔗 Project Page

https://chuny1.github.io/3DGPT/3dgpt.html


🚀 Current & Upcoming Releases

This repository is part of the official implementation of our paper, 3D-GPT: Procedural 3D Modeling with Large Language Models. We are gradually releasing different components of our project according to the following plan:

✅ Current Release: Agent Implementation

We are currently releasing the agent implementation, which includes:

  • The core agent logic
  • Example usage demonstrating how to call the agent to generate a Python script that can control the Infinigen generation.
  • The LLM/agents/ directory contains the implementation of two agents.
  • The LLM/documents/ directory contains the example function documentation format, where you can add functions as many as you want.
  • Running LLM/parser.py will provide detailed output about how different agents interact with each other and how it infers function parameters.

🔜 Upcoming Releases

We have made significant modifications to many functions, making them easier for LLMs to understand while enhancing their control capabilities. Our upcoming releases include:

  • Modified Infinigen (by March 25, before 3DV conference): We will provide our modified version of Infinigen, improving its adaptability to LLM-generated scripts.
  • LLM Parser Enhancement: Instead of generating Python scripts, the LLM parser will generate a configuration file to control Infinigen. This change will make the process more user-friendly and support human-assisted editing.

Stay tuned for these updates!


🛠 Installation & Usage

Follow the instructions below to set up and run the current release:

1️⃣ Install Infinigen

Follow the official Infinigen repository for installation and setup: https://github.com/princeton-vl/infinigen

2️⃣ Install Dependencies

# Clone the repository
git clone [email protected]:Chuny1/3DGPT.git

# Install required Python packages
pip install openai==0.27.8

3️⃣ Setup OpenAI API Key

To use OpenAI's LLMs, you need to obtain an API key:

  • Visit the OpenAI website and generate an API key.
  • Add your personal API key to parser.py. Do not share your API key.

api key

4️⃣ Choose GPT Model

You can select the GPT model you want to use by visiting: https://platform.openai.com/docs/api-reference/chat

5️⃣ Run the Agent

python LLM/parser.py

📚 Citation

If you find this work useful, please consider citing our paper:

@article{sun20233d,
  title={3d-gpt: Procedural 3d modeling with large language models},
  author={Sun, Chunyi and Han, Junlin and Deng, Weijian and Wang, Xinlong and Qin, Zishan and Gould, Stephen},
  journal={arXiv preprint arXiv:2310.12945},
  year={2023}
}

관련 프로젝트 살펴보기

불러오는 중…