five

hong136/FullCircle

收藏
Hugging Face2026-04-05 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/hong136/FullCircle
下载链接
链接失效反馈
官方服务:
资源简介:
--- license: apache-2.0 tags: - Graphics - 3D_reconstruction - Fisheye pretty_name: FullCircle --- # FullCircle Dataset Dataset for [**FullCircle: Effortless 3D Reconstruction from Casual 360° Captures**](https://arxiv.org/abs/2603.22572). [![Webpage](https://img.shields.io/badge/Webpage-1F6FEB?style=for-the-badge&logo=googlechrome&logoColor=white)](https://theialab.github.io/fullcircle/) [![arXiv](https://img.shields.io/badge/arXiv-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.22572) [![Code](https://img.shields.io/badge/Code-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/theialab/fullcircle) ## Structure Each scene is organized as follows: ``` <scene_name>/ ├── images/ # fisheye frames (camera1/, camera2/) ├── masks/ # fisheye masks (camera1/, camera2/) ├── omni/images/ # 360° omnidirectional frames └── sparse/0/ # COLMAP reconstruction ``` ## Usage Place scenes under `data/` in the code repository, then follow the training instructions in the [code repo](https://github.com/theialab/fullcircle). ## Citation ```bibtex @article{foroutan2026fullcircle, title = {FullCircle: Effortless 3D Reconstruction from Casual 360° Captures}, author = {Foroutan, Yalda and Oztas, Ipek and Rebain, Daniel and Dundar, Aysegul and Yi, Kwang Moo and Goli, Lily and Tagliasacchi, Andrea}, journal = {arXiv preprint arXiv:2603.22572}, year = {2026} } ```

许可证:Apache-2.0 标签: - 图形学(Graphics) - 三维重建(3D_reconstruction) - 鱼眼镜头(Fisheye) 展示名称:FullCircle # FullCircle 数据集 本数据集对应论文[**FullCircle:基于随手拍摄的360°素材实现无负担三维重建**](https://arxiv.org/abs/2603.22572)。 [![项目主页](https://img.shields.io/badge/Webpage-1F6FEB?style=for-the-badge&logo=googlechrome&logoColor=white)](https://theialab.github.io/fullcircle/) [![arXiv预印本](https://img.shields.io/badge/arXiv-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.22572) [![代码仓库](https://img.shields.io/badge/Code-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/theialab/fullcircle) ## 数据集组织结构 每个场景的组织结构如下: <scene_name>/ ├── images/ # 鱼眼帧(包含camera1/、camera2/子目录) ├── masks/ # 鱼眼掩码(包含camera1/、camera2/子目录) ├── omni/images/ # 360°全景帧 └── sparse/0/ # COLMAP重建结果 ## 使用方法 将所有场景文件夹放置于代码仓库的`data/`目录下,随后按照[代码仓库](https://github.com/theialab/fullcircle)中的训练指引进行操作。 ## 引用格式 bibtex @article{foroutan2026fullcircle, title = {FullCircle: Effortless 3D Reconstruction from Casual 360° Captures}, author = {Foroutan, Yalda and Oztas, Ipek and Rebain, Daniel and Dundar, Aysegul and Yi, Kwang Moo and Goli, Lily and Tagliasacchi, Andrea}, journal = {arXiv preprint arXiv:2603.22572}, year = {2026} }
提供机构:
hong136
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作