VQMT3D Project

Конактное лицо: Дмитрий Сергеевич Ватолин (dmitriy@graphics.cs.msu.ru)

October 22, 2014: Report #7 released!

Introduction

VQMT3D (Video Quality Measurement Tool 3D) project was created to improve stereoscopic films. Our aim is to help filmmakers produce high-quality 3D video by finding inexpensive ways of automatically enhancing film quality.

VQMT3D project is currently being developed. On this page we will collect recent information about the project.

List of Metrics

We have developed metrics for stereoscopic video that was captured with a system of two cameras (stereo rig).
The following metrics are in use:

11 metrics

Vertical Parallax
Scale Mismatch
Rotation Mismatch
Color Mismatch
Sharpness Mismatch
Depth Budget
Depth Continuity
Stereo Window Violation Perceptibility
Temporal Shift
Channel Mismatch (Swapped views)
Crosstalk Perceptibility

Metrics for converted stereoscopic video are currently being developed.

Visualizations of detected problems enable a possibility of clear stereoscopic problem understanding with just one picture. The following pictures are examples of found problems and of these visualizations, too.

An example of detected strong horizontal disparity. Frame #22030 from Galapagos: The Enchanted Voyage

An example of detected vertical disparity. Frame #19105 from Galapagos: The Enchanted Voyage

An example of detected color mismatch. Frame #53725 from Galapagos: The Enchanted Voyage

An example of detected sharpness mismatch. Frame #25100 from Galapagos: The Enchanted Voyage

Reports overview

7 reports

  1. S3D shooting quality analysis of 5 movies
  2. S3D shooting quality analysis of 5 movies
  3. 2D-3D conversion quality analysis of 5 movies
  4. S3D shooting quality analysis of 5 movies
  5. 2D-3D conversion quality analysis of 5 movies
  6. Stereo Window analysis of 10 movies
  7. Stereo Window analysis of 10 movies

2 reports

coming soon

  1. Rotate Analysis, Temporal Shift, Channels Swap, Zoom Mismatch in 25 movies
  2. Color Mismatch, Sharpness Mismatch, Temporal Shift, Channels Swap etc in 100 movies

Report 1 (S3D shooting quality analysis of 5 movies)

Release date: March 7, 2013

Download (Additional info for bloggers and press)

Pages: 246;   Figures: 295

Film list:

  • Pirates of the Caribbean: On Stranger Tides
  • Resident Evil: Afterlife
  • Step Up 3D
  • Galapagos: The Enchanted Voyage
  • Into the Deep

Film list:

  • Dolphin Tale
  • Drive Angry
  • Hugo
  • The Three Musketeers
  • Sanctum

Film list:

  • Alice in Wonderland
  • Clash of the Titans
  • Conan the Barbarian
  • Green Lantern
  • Abraham Lincoln: Vampire Hunter

Report 4 (S3D shooting quality analysis of 5 movies)

Release date: October 1, 2013

Download

Pages: 301;   Figures: 402

Film list:

  • A Very Harold & Kumar 3D Christmas
  • Pina
  • Step Up Revolution
  • Resident Evil 5: Retribution
  • The Amazing Spider-Man

Film list:

  • The Avengers
  • The Chronicles of Narnia: The Voyage of the Dawn Treader
  • Gulliver’s Travels
  • Immortals
  • Wrath of the Titans

Report 6 (Stereo Window analysis of 10 movies)

Release date: September 10, 2014

Download (Additional info for bloggers and press)

Pages: 415;   Figures: 455

Film list:

  • The Amazing Spiderman
  • The Three Musketeers
  • Pirates of the Caribbean: On Stranger Tides
  • Dolphin Tale
  • Drive Angry
  • The Avengers
  • John Carter
  • G-Force
  • Abraham Lincoln: Vampire Hunter
  • Clash of the Titans

Report 7 (Stereo Window analysis of 10 movies)

Release date: October 22, 2014

Download (Additional info for bloggers and press)

Pages: 333;   Figures: 348

Film list:

  • Pina
  • Step Up Revolution
  • Resident Evil: Retribution
  • Hugo
  • Immortals
  • A Very Harold & Kumar 3D Christmas
  • Green Lantern
  • Conan the Barbarian
  • Wrath of the Titans
  • Alice in Wonderland

Report 8 (Rotate Analysis, Temporal Shift, Channels Swap, Zoom Mismatch in 25 movies)

Approximate release date: 4th quarter of 2014

Analysis of previously evaluated films

Report 9 (Color Mismatch, Sharpness Mismatch, Temporal Shift, Channels Swap etc in 100 movies)

Approximate release date: 4th quarter of 2014

Analysis of 100 movies

Invitation to the Project

We invite stereographers, researchers and proofreaders to join our 3D-film analysis project. We are open for collaboration and appreciate your ideas and contributions. We love to receive feedback and learn from the experience of people in the film-production industry.

If you would like to participate, please contact us: 3DMovieTest@graphics.cs.msu.ru.

Stereographers

Currently, we are preparing our first reports on stereo-video quality of full-length films. We invite professional stereographers to comment on our reports. Our expertise is in research and in creating metrics, but the causes of some artifacts may be unclear for us. Analyzing these causes and estimating the severity of artifacts are a crucial part of our reports, so we welcome expert comments on these issues.

Every comment in the final report will be attributed to its respective author. We expect that some people will select comments of a concrete author, and we wish that your comments will be selected. Our hope is that these comments will all be beneficial for our readers.

If you are currently working on a film project, you may be interested in discussing the possibility of analyzing your film, or some portion thereof, before its release to help improve its 3D quality.

Researchers

Researchers working on stereoscopic quality assessment are welcome to collaborate with us on our project. We can run your algorithms on huge amounts of data and jointly publish the results.

We have developed a system to calculate metrics for full-length films. These metrics are loaded into the system as plug-ins, and our SDK for creating metrics is available on request. Thus, researchers need only provide binaries—algorithms and source code can remain confidential.

Calculations for one film take about a week (this estimate is for a full-length film, with calculations performed using three computers). GPGPU acceleration (CUDA or OpenCL) is available.

For researchers who would like to participate, we recommend sending us metrics that are already or soon to be published. Inclusion in our report may increase your citation index and the reputation of your work among experts. We can provide raw results from your metric for in-depth analysis or for use in literature. If your metric turns out to be useful, we will gladly include your results in our film comparison.

Proofreaders

We welcome readers who have strong English skills or who can help improve the clarity of our literature.

Any reader that offers numerous constructive comments on how to fix errors or otherwise improve the report will be included in the authors list. Everyone who help us improve our reports will be mentioned in the acknowledgments section.

Most importantly, proofreaders who are willing to help us improve our reports will be among the first to receive draft versions (under the condition of a signed nondisclosure agreement).

Contacts

For questions and proposition please contact us: 3DMovieTest@graphics.cs.msu.ru.

Участники

Публикации

Благодарности

We wish to acknowledge the help provided by CMC Faculty of Lomonosov Moscow State University.
CMC Faculty provided us with extra computational capabilities and disk space which was needed for our research.
This work is partially supported by the Intel/Cisco Video Aware Wireless Network (VAWN) Program and by grant 10-01-00697a from the Russian Foundation for Basic Research.