Документ взят из кэша поисковой машины. Адрес
оригинального документа
: http://graphics.cs.msu.ru/ru/node/1237
Дата изменения: Sun Apr 10 00:43:00 2016 Дата индексирования: Sun Apr 10 00:43:00 2016 Кодировка: UTF-8 |
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.
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
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
7 reports
2 reports
coming soon
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:
|
||
Report 2 (S3D shooting quality analysis of 5 movies) Release date: May 31, 2013 Download (Additional info for bloggers and press) Pages: 342; Figures: 442 |
Film list:
|
||
Report 3 (2D-3D conversion quality analysis of 5 movies) Release date: August 28, 2013 Download (Additional info for bloggers and press) Pages: 305; Figures: 336 |
Film list:
|
||
Report 4 (S3D shooting quality analysis of 5 movies) Release date: October 1, 2013 Pages: 301; Figures: 402 |
Film list:
|
||
Report 5 (2D-3D conversion quality analysis of 5 movies) Release date: April 11, 2014 Download (Additional info for bloggers and press) Pages: 384; Figures: 404 |
Film list:
|
||
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:
|
||
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:
|
||
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 |
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.
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 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.
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).
For questions and proposition please contact us: 3DMovieTest@graphics.cs.msu.ru.
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.