# MIDI

**Repository Path**: greatjinyun/MIDI

## Basic Information

- **Project Name**: MIDI
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-02-25
- **Last Updated**: 2025-02-25

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

## 🏠 <a href="https://huanngzh.github.io/MIDI-Page/" target="_blank">Project Page</a> | <a href="https://arxiv.org/abs/2412.03558" target="_blank">Paper</a>

![teaser](assets/doc/teaser.png)

MIDI is a **novel paradigm** for compositional 3D scene generation from a single image. MIDI extends pre-trained image-to-3D object generation models to **multi-instance diffusion models**, enabling the simultaneous generation of multiple 3D instances with accurate spatial relationships and high generalizability.

## Citation

```
@article{huang2024midi,
  title={MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation},
  author={Huang, Zehuan and Guo, Yuanchen and An, Xingqiao and Yang, Yunhan and Li, Yangguang and Zou, Zixin and Liang, Ding and Liu, Xihui and Cao, Yanpei and Sheng, Lu},
  journal={arXiv preprint arXiv:2412.03558},
  year={2024}
}
```