Matterport3D 360° RGBD Dataset

This dataset is an extension of Matterport3D that contains data to train and validate high resolution 360 monocular depth estimation models. The data is structured in 90 folders belonging to 90 different buildings storing a total of 9684 samples. Each sample of the dataset consists of 4 files: the RGB equirectangular 360 image (.png), its depth ground-truth (.dpt), a visualisation of the depth ground-truth (.png) and the camera to world extrinsic parameters for the image (.txt) saved as 7 parameters: 3 for the camera center and the last 4 for the XYWZ rotation quaternion.

Keywords:
360 Monocular Depth Estimation, Virtual Reality, 3D geometry
Subjects:
Information and communication technologies

Cite this dataset as:
Rey-Area, M., Yuan, M., Richardt, C., 2022. Matterport3D 360° RGBD Dataset. Bath: University of Bath Research Data Archive. Available from: https://doi.org/10.15125/BATH-01126.

Export

[QR code for this page]

Data

data_00.zip
application/zip (12GB)
Creative Commons: Attribution 4.0

data_01.zip
application/zip (13GB)
Creative Commons: Attribution 4.0

data_02.zip
application/zip (11GB)
Creative Commons: Attribution 4.0

data_03.zip
application/zip (11GB)
Creative Commons: Attribution 4.0

data_04.zip
application/zip (11GB)
Creative Commons: Attribution 4.0

data_05.zip
application/zip (11GB)
Creative Commons: Attribution 4.0

data_06.zip
application/zip (9GB)
Creative Commons: Attribution 4.0

Creators

Mingze Yuan
University of Bath

Contributors

University of Bath
Rights Holder

Matterport3D authors
Data Collector

Documentation

Methodology link:

Rey-Area, M., Yuan, M., and Richardt, C., 2021. 360MonoDepth: High-Resolution 360° Monocular Depth Estimation. Version 2. arXiv. Available from: https://doi.org/10.48550/ARXIV.2111.15669.

Documentation Files

README.md
text/plain (3kB)
Creative Commons: Attribution 4.0

Funders

Engineering and Physical Sciences Research Council
https://doi.org/10.13039/501100000266

EPSRC Centre for Doctoral Training in Digital Entertainment
EP/L016540/1

Engineering and Physical Sciences Research Council
https://doi.org/10.13039/501100000266

Fellowship - Towards Immersive 360° VR Video with Motion Parallax
EP/S001050/1

Engineering and Physical Sciences Research Council
https://doi.org/10.13039/501100000266

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) - 2.0
EP/T022523/1

Publication details

Publication date: 25 March 2022
by: University of Bath

Version: 1

DOI: https://doi.org/10.15125/BATH-01126

URL for this record: https://researchdata.bath.ac.uk/id/eprint/1126

Related papers and books

Rey-Area, M., Yuan, M., and Richardt, C., 2022. 360MonoDepth: High-Resolution 360° Monocular Depth Estimation. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. Available from: https://doi.org/10.1109/cvpr52688.2022.00374.

Related datasets and code

Chang, A., Dai, A., Funkhouser, T., Halber, M., Niessner, M., Savva, M., Song, S., Zeng, A., and Zhang, Y., n.d. Matterport3D. GitHub. Available from: https://github.com/niessner/Matterport.

Related online resources

Rey-Area, M., Yuan, M., and Richardt, C., 2022. 360MonoDepth: High-Resolution 360° Monocular Depth Estimation. GitHub. Available from: https://manurare.github.io/360monodepth/.

Contact information

Please contact the Research Data Service in the first instance for all matters concerning this item.

Contact person: Manuel Rey-Area

Departments:

Faculty of Science
Computer Science

Research Centres & Institutes
Centre for Digital Entertainment (CDE)
Centre for the Analysis of Motion, Entertainment Research & Applications