Idea23D

[COLING 2025] Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs

Idea23D evaluation dataset

Full inference code can be found at:

<div align="left"> <a href="https://idea23d.github.io/"><img src="https://img.shields.io/static/v1?label=Homepage&message=Idea23D&color=blue&logo=github-pages"></a><a href="https://github.com/yisuanwang/Idea23D"><img src="https://img.shields.io/github/stars/yisuanwang/Idea23D?label=stars&logo=github&color=brightgreen" alt="GitHub Repo Stars"></a><a href="https://arxiv.org/abs/2404.04363"><img src="https://img.shields.io/badge/arXiv-2404.04363-b31b1b.svg?style=flat-square" alt="arXiv"></a> <a href="https://huggingface.co/yisuanwang/Idea23D"><img src="https://img.shields.io/static/v1?label=Dataset&message=HuggingFace&color=yellow"></a><a href="https://idea23d.github.io"><img src="https://img.shields.io/static/v1?label=Demo&message=Gradio&color=yellow"></a> </div>

✨Introduction

Based on the LMM we developed Idea23D, a multimodal iterative self-refinement system that enhances any T2I model for automatic 3D model design and generation, enabling various new image creation functionalities togther with better visual qualities while understanding high level multimodal inputs.

📜Citations

@article{chen2024idea23d,
  title={Idea-2-3D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs}, 
  author={Junhao Chen and Xiang Li and Xiaojun Ye and Chao Li and Zhaoxin Fan and Hao Zhao},
  year={2024},
  eprint={2404.04363},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

⭐️ Star History