Datasets for “OmniPhotos: Casual 360° VR Photography”

This dataset contains the raw and processed data used to validate the results for the paper. Each subdirectory in the Preprocessed and Unprocessed folders contains a 360° video captured in a circle at different locations in the world, using an Insta360 One X 360° camera on a rotating selfie stick. These subdirectories are named after these locations. Both the proprietary (.insv) video format, as well as a stitched equirectangular (.mp4) video (used by our preprocessing pipeline), have been included. As well as these videos, each subdirectory contains the Input frames, used by our software to display the scene, a Capture directory that contains structure-from-motion data for the given scene, as well as a Config directory, which contains necessary configuration files to run our software.

In the Preprocessed directory, the subdirectories also contain a Cache directory, containing optical flow (.floss) files, a CSV file linking the floss files to the relevant images in Input, and .obj files that contain the scene-dependent proxy mesh (deformed sphere) used to render the scene.

Keywords:
Virtual Reality, Novel View Synthesis, Casual Capture, Image-Based Rendering, Motion Parallax

Cite this dataset as:
Bertel, T., Yuan, M., Lindroos, R., Richardt, C., 2020. Datasets for “OmniPhotos: Casual 360° VR Photography”. Bath: University of Bath Research Data Archive. Available from: https://doi.org/10.15125/BATH-00922.

Export

[QR code for this page]

Access restrictions apply: In this version, the first scene in Preprocessed.zip ("Ballintoy") is missing the fitted scene-adaptive proxy geometry, and the scene "Crescent" in Unpreprocessed.zip contains an incorrect number of frames in the config file. Please refer to version 2 of the dataset for the corrected files.

Creators

Tobias Bertel
University of Bath

Mingze Yuan
University of Bath

Reuben Lindroos
University of Bath

Contributors

University of Bath
Rights Holder

Documentation

Data collection method:

Full details of the methodology may be found in the associated paper.

Funders

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

6-DoF VR Video: Towards Immersive 360-degree VR Video with Motion Parallax
EP/S001050/1

Publication details

Publication date: 26 November 2020
by: University of Bath

Version: 1

WarningThere is a more recent version of this item available.
  • Version 1. (26 November 2020) [Currently Displayed]
  • Version 2. (18 December 2020)

DOI: https://doi.org/10.15125/BATH-00922

URL for this record: https://researchdata.bath.ac.uk/id/eprint/922

Related papers and books

Bertel, T., Yuan, M., Lindroos, R. and Richardt, C., 2020. OmniPhotos. ACM Transactions on Graphics, 39(6), pp.1-12. Available from: https://doi.org/10.1145/3414685.3417770.

Contact information

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

Contact person: Reuben Lindroos

Departments:

Faculty of Science
Computer Science

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