The ninth report presents results from an analysis of 105 S3D movies that examined temporal shifts between views and introduces a new metric for detecting stuck-to-background objects in converted S3D scenes. The report also introduces a classifier that determines which technique was used during production of a scene (capture, conversion or CGI).

Download report

Examined problems:

• Temporal shift
• Stuck-to-background objects
• Detection of 2D-3D conversion and natively captured shots

The report comprises three main parts:

1. Firstly, we present our approach to analyzing stereoscopic video for temporal shift. We provide the results of our analysis for 105 S3D films and present overall charts for these films.
2. Then we present our new metric for detecting foreground objects stuck to the background of a scene. The report also presents visualizations of these scenes.
3. Finally, we introduce our algorithm which classifies shots in S3D films into three categories: natively captured, 2D-3D converted and CGI. The section contains a lot of examples with converted shots in natively captured films and natively captured shots in converted S3D films.

Example of a "stuck-to-background" object

Professional stereographers have contributed to the analysis by providing valuable comments and general feedback.

When you want to make a reference to this project, please refer one of the following publications:

1. Mikhail Erofeev, Dmitriy Vatolin, Alexander Voronov, Alexey Fedorov,
   “Toward an Objective Stereo-Video Quality Metric: Depth Perception of Textured Areas,” [pdf]
   International Conference on 3D Imaging (IC3D),
   pp. 1–6, 2012. doi:10.1109/IC3D.2012.6615120
2. D. Akimov, A. Shestov, A. Voronov, D. Vatolin,
   “Automatic Left-Right Channel Swap Detection,” [pdf]
   International Conference on 3D Imaging (IC3D),
   pp. 1–6, 2012. doi:10.1109/IC3D.2012.6615126
3. A. Voronov, A. Borisov, D. Vatolin,
   “System for Automatic Detection of Distorted Scenes in Stereo Video,” [pdf]
   Proceedings of the Sixth International Workshop on Video Processing and Quality Metrics (VPQM),
   2012.
4. A. Voronov, D. Vatolin, D. Sumin, V. Napadovsky, A. Borisov,
   “Towards Automatic Stereo-video Quality Assessment and Detection of Color and Sharpness Mismatch,” [pdf]
   International Conference on 3D Imaging (IC3D),
   pp. 1–6, 2012. doi:10.1109/IC3D.2012.6615121
5. A. Voronov, D. Vatolin, D. Sumin, V. Napadovsky, and A. Borisov,
   “Methodology for stereoscopic motion-picture quality assessment,” [pdf]
   Proc. SPIE 8648, Stereoscopic Displays and Applications XXIV,
   vol. 8648, pp. 864810-1–864810-14, March 2013. doi:10.1117/12.2008485
6. A. Bokov, D. Vatolin, A. Zachesov, A. Belous, and M. Erofeev,
   “Automatic detection of artifacts in converted S3D video,” [pdf]
   Proc. SPIE 9011, Stereoscopic Displays and Applications XXV,
   vol. 9011, pp. 901112-1–901112-14, March 2014. doi:10.1117/12.2054330

Full report (467 pages) is absolutely free but download is available only for industry professionals (due to publication of real mistakes in the post-production process).

To download the report, please fill-in the request form.
You will get the download link for all reports (Reports #1–9) via e-mail.

Contacts

For questions and proposition please contact us