数据集需从项目页 download 页面单独下载,不在仓库内;使用前需参考 data_preprocess 目录中的代码进行预处理

git clone https://github.com/xiaobiaodu/3DRealCar_Toolkit.gitREADME 未说明
ICCV2025 开源的大规模真实车辆 RGB-D 数据集,提供 360 度环视图像与点云,用于三维车辆重建研究
提供真实场景下 360 度环视的 RGB-D 汽车数据集,配套 3D 重建与高斯泼溅工具,用于车辆三维建模研究和评测。
核心能力
- 提供密集采集的 RGB-D 图像与点云
- 每辆车含 360 度环视视角
- 首个提供 3D 车辆解析图标注的数据集
- Apache-2.0 许可,允许免费商用
- 附带 data_preprocess 数据预处理代码
容易踩的坑
暂无 release 数据(可能没有发版,或尚未同步)。
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
Project page | Paper
Free Commercial Usage
3DRealCar dataset is allowed commercial usage for free. The dataset license is Apache-2.0.
😮 Highlights
- Our 3DRealCar is the first large-scale 3D real car dataset containing both densely captured RGB-D images and point clouds.
- This dataset is the first to provide 3D car parsing map annotations.
🚩 Updates
Welcome to watch 👀 this repository for the latest updates.
✅ [2024.6.10] : We have released our paper, 3DRealCar on arXiv.
✅ [2024.6.10] : Release project page.
✅ [2024.8.13] : Code is realeased.
✅ [2024.8.15] : We are releasing our dataset. You can download our dataset in the project page.
✅ [2025.1.21] : Release 3DRealCar dataset download page.
How to use
Please refer to our code data_preprocess
✏️ Citation
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.
@article{du20243drealcar,
title={3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views},
author={Du, Xiaobiao and Sun, Haiyang and Wang, Shuyun and Wu, Zhuojie and Sheng, Hongwei and Ying, Jiaying and Lu, Ming and Zhu, Tianqing and Zhan, Kun and Yu, Xin},
journal={arXiv preprint arXiv:2406.04875},
year={2024}
}