graviti
产品服务
解决方案
知识库
公开数据集
关于我们
avatar
RealEstate 10K
许可协议: CC-BY 4.0

Overview

RealEstate10K is a large dataset of camera poses corresponding to 10 million frames derived from about 80,000 video clips, gathered from about 10,000 YouTube videos. For each clip, the poses form a trajectory where each pose specifies the camera position and orientation along the trajectory. These poses are derived by running SLAM and bundle adjustment algorithms on a large set of videos.

Citation

Please use the following citation when referencing the dataset:

@article{46965,
title = {Stereo Magnification: Learning view synthesis using multiplane images},
author = {Tinghui Zhou and Richard Tucker and John Flynn and Graham Fyffe and Noah Snavely},
year = {2018},
URL = {https://arxiv.org/abs/1805.09817},
journal = {ACM Trans. Graph. (Proc. SIGGRAPH)},
volume = {37}
}
数据概要
数据格式
数据量
80K
文件大小
720MB
| 数据量 80K | 大小 720MB
RealEstate 10K
许可协议: CC-BY 4.0

Overview

RealEstate10K is a large dataset of camera poses corresponding to 10 million frames derived from about 80,000 video clips, gathered from about 10,000 YouTube videos. For each clip, the poses form a trajectory where each pose specifies the camera position and orientation along the trajectory. These poses are derived by running SLAM and bundle adjustment algorithms on a large set of videos.

Citation

Please use the following citation when referencing the dataset:

@article{46965,
title = {Stereo Magnification: Learning view synthesis using multiplane images},
author = {Tinghui Zhou and Richard Tucker and John Flynn and Graham Fyffe and Noah Snavely},
year = {2018},
URL = {https://arxiv.org/abs/1805.09817},
journal = {ACM Trans. Graph. (Proc. SIGGRAPH)},
volume = {37}
}
0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号

Copyright@Graviti
沪ICP备19019574号
沪公网安备 31011002004865号