Earth observation processing framework for machine learning in Python.
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
C++
Category
Model Development
Subcategory
Dataset engineering
Keywords
3D
Stars
1,261
Forks
155
Contributors
7
Created date
2016-12-15
Updated date
2026-10-08
Stars in 1 day
0
Stars in 7 days
0
Rank
10,923
Previous rank
10,891
Rank change
-32
7-day stars rank
12,820
Previous 7-day stars rank
10,053
7-day stars rank change
-2,767
Total stars rank
9,312
Previous total stars rank
9,297
Total stars rank change
-15
Country
Germany
README summary
0 dataset contains data captured throughout 90 properties with a Matterport Pro Camera. This repository includes the raw data for the dataset plus derived data, annotated data, and scripts/models for several scene understanding tasks. Visit the main website for updates and to browse the data. Paper **Matterport3D: Learning from RGB-D Data in Indoor Environments** If you use the Matterport3D data or code please cite: Data The dataset consists of several types of annotations: color and depth images, camera
poses, textured 3D meshes, building floor plans and region annotations, object instance semantic annotations. For details see the data organization document. To download the dataset, you must indicate that you agree to the terms of use by signing the Terms of Use agreement form, using your institutional email addresses, and sending it to: matterport3d@googlegroups. We will then provide download access to the dataset. Benchmark tasks Using the Matterport3D data, we present several benchmark tasks: image keypoint matching, view overlap
prediction, surface normal estimation, region type classification, and semantic voxel labeling. Tools We provide code for loading and viewing the data. License The data is released under the Matterport3D Terms of Use, and the code is released under the MIT license.
Frequently asked questions
How many stars and forks are recorded?
niessner/Matterport has 1,261 stars and 155 forks.
What is the repository rank?
niessner/Matterport is ranked 10,923.
What language and category are recorded?
niessner/Matterport has 1,261 stars, uses C++ and belongs to Model Development.
Which repository is closest in rank?
niessner/Matterport is compared with openpifpaf/openpifpaf, ranked 10,924 with 1,261 stars.
README
Matterport3D
The Matterport3D V1.0 dataset contains data captured throughout 90 properties with a Matterport Pro Camera.
This repository includes the raw data for the dataset plus derived data, annotated data, and scripts/models for several scene understanding tasks.
Visit the main website for updates and to browse the data.
If you use the Matterport3D data or code please cite:
@article{Matterport3D,
title={{Matterport3D}: Learning from {RGB-D} Data in Indoor Environments},
author={Chang, Angel and Dai, Angela and Funkhouser, Thomas and Halber, Maciej and Niessner, Matthias and Savva, Manolis and Song, Shuran and Zeng, Andy and Zhang, Yinda},
journal={International Conference on 3D Vision (3DV)},
year={2017}
}
Data
The dataset consists of several types of annotations: color and depth images, camera poses, textured 3D meshes, building floor plans and region annotations, object instance semantic annotations. For details see the data organization document.
To download the dataset, you must indicate that you agree to the terms of use by signing the Terms of Use agreement form, using your institutional email addresses, and sending it to: matterport3d@googlegroups.com. We will then provide download access to the dataset.
Benchmark tasks
Using the Matterport3D data, we present several benchmark tasks: image keypoint matching, view overlap prediction, surface normal estimation, region type classification, and semantic voxel labeling. See the tasks directory for details.
Tools
We provide code for loading and viewing the data. See the code directory for details.
License
The data is released under the Matterport3D Terms of Use, and the code is released under the MIT license.
