Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/flymin/magicdrive3d

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”
https://github.com/flymin/magicdrive3d

3d autonomous-driving diffusion-models scene-generation

Last synced: 8 days ago
JSON representation

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

Host: GitHub
URL: https://github.com/flymin/magicdrive3d
Owner: flymin
License: agpl-3.0
Created: 2024-06-08T01:51:42.000Z (8 months ago)
Default Branch: main
Last Pushed: 2024-06-08T02:22:51.000Z (8 months ago)
Last Synced: 2024-11-21T23:57:40.728Z (2 months ago)
Topics: 3d, autonomous-driving, diffusion-models, scene-generation
Homepage: https://gaoruiyuan.com/magicdrive3d/
Size: 16.6 KB
Stars: 267
Watchers: 9
Forks: 4
Open Issues: 1
Metadata Files:
- Readme: README.MD
- License: LICENSE

Awesome Lists containing this project

README

        # MagicDrive3D

[![arXiv](https://img.shields.io/badge/ArXiv-2405.14475-b31b1b.svg?style=plastic)](https://arxiv.org/abs/2405.14475) [![web](https://img.shields.io/badge/Web-MagicDrive3D-blue.svg?style=plastic)](https://gaoruiyuan.com/magicdrive3d/) [![license](https://img.shields.io/github/license/flymin/MagicDrive3D?style=plastic)](https://github.com/flymin/MagicDrive3D/blob/main/LICENSE) [![star](https://img.shields.io/github/stars/flymin/MagicDrive3D)](https://github.com/flymin/MagicDrive3D)

This repository contains the implementation of the paper.

If you find our work useful, Please give us a star 🌟!

> MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes 


> [Ruiyuan Gao](https://gaoruiyuan.com/)¹, [Kai Chen](https://kaichen1998.github.io/)², [Zhihao Li](https://github.com/zhihaolee)³, [Lanqing Hong](https://scholar.google.com.sg/citations?user=2p7x6OUAAAAJ&hl=en)^{3^}, [Zhenguo Li](https://scholar.google.com/citations?user=XboZC1AAAAAJ&hl=en)³, [Qiang Xu](https://cure-lab.github.io/)^{1^}


> ¹CUHK ²HKUST ³Huawei Noah's Ark Lab 


> ^{^}Corresponding Authors

## Plan

We will release the code for scene reconstruction in this repo.

As for upgrades in video generation, we will merge the implementation to [MagicDrive-t](https://github.com/cure-lab/MagicDrive/tree/video) (i.e., video branch of [MagicDrive](https://github.com/cure-lab/MagicDrive)).

## Cite Us

```bibtex

@article{gao2024magicdrive3d,

  title={{MagicDrive3D}: Controllable 3D Generation for Any-View Rendering in Street Scenes},

  author={Gao, Ruiyuan and Chen, Kai and Li, Zhihao and Hong, Lanqing and Li, Zhenguo and Xu, Qiang},

  journal={arXiv preprint arXiv:2405.14475},

  year={2024}

}

@inproceedings{gao2023magicdrive,

  title={{MagicDrive}: Street View Generation with Diverse 3D Geometry Control},

  author={Gao, Ruiyuan and Chen, Kai and Xie, Enze and Hong, Lanqing and Li, Zhenguo and Yeung, Dit-Yan and Xu, Qiang},

  booktitle = {International Conference on Learning Representations},

  year={2024}

}

```

## Credit

We adopt the following open-sourced projects:

- [MagicDrive](https://github.com/cure-lab/MagicDrive): controllable street view video generation

- [gaussian-splatting](https://github.com/graphdeco-inria/gaussian-splatting): 3D reconstruction

- [ZoeDepth](https://github.com/isl-org/ZoeDepth): monocular metric depth estimation