vsenseODVQ | V-SENSE Omnidirectional Video Quality Database

---

Omnidirectional video (also known as 360-degree video) is spherical in nature, as it represents all the light rays converging on a fixed point in space. Due to this spherical nature, watching the entire ODV is not possible for a human observer, which makes visual attention important for compression, transmission, and quality assessment.

As part of our paper titled “Visual attention-aware quality estimation framework for omnidirectional video using spherical Voronoi diagram“, we release a database as described below. If you use this publicly available dataset, please cite our paper in your publication as indicated below.

For more information, you can check the research webpage: [VIVA-Q: Voronoi-based Quality Assessment Framework for Omnidirectional Video].

DATABASE DETAILS

The database contains:

• The mean opinion scores for all 120 compressed ODV sequences (from 8 reference ODVs), collected from more than 23 participants, and
• the head-mounted display (HMD) viewpoint directions for all the participants.

DOWNLOADS

To download the vsenseODVQ (V-SENSE Omnidirectional Video Quality Database), contact us at crocis@scss.tcd.ie.

Please kindly cite our paper in your publication if you use this database:

• S. Croci, C. Ozcinar, E. Zerman, S. Knorr, J. Cabrera, A. Smolic “Visual attention-aware quality estimation framework for omnidirectional video using spherical voronoi diagram,” Quality and User Experience, volume 5, April 2020.

@article{croci2020visual,
  author       = "Croci, Simone and Ozcinar, Cagri and Zerman, Emin and Knorr, Sebastian and Cabrera, Juli\'{a}n and Smolic, Aljosa",
  title        = "Visual attention-aware quality estimation framework for omnidirectional video using spherical voronoi diagram",
  journal      = "Quality and User Experience",
  volume       = "5",
  number       = "4",
  year         = "2020",
  publisher    = "Springer",
  doi          = "10.1007/s41233-020-00032-3"
}