MSU 3D Video Capture for glasses-free 3D displays
- Project: Dr. Dmitriy Vatolin
- Implementation, algorithm: Sergey Grishin, Karen Simonyan, Sergey Matyunin
The technology of the 3D video creating has long history. Playback equipment imperfections and the complexity of the creating three-dimensional films always prevented the spread of the 3D video technology. Scientists are near to the solution of the first problem: they have already developed monitors which don’t require neither special glasses nor other extra devices for viewing. 3D video making still requires expensive high-quality equipment and therefore it’s almost inaccessible for general users. our laboratory was challenged to make a 3d film using cheap widespread devices - web-cameras.
We used two web-cameras for the video capture and monitor Spatial View 19’’ for camera tunning and video demonstration.
The given display creates 3D effect using 5 views from different camera points. We got two of them directly from the cameras and the rest views were generated by MSU Stereo To Multiview Conversion method developed by our library. Similar video sequence was generated for 9-view monitor.
|Interpolation of the intermediate views|
Video from cameras have significant brightness/white balance difference. It can cause conversion artefacts. So preprocessing is required. Semiautomatic video-filter for the smoothing of the differences in the color rendition between the cameras was developed.
How to view 3D video
To view 3D images you need autostereoscopic monitor and specialized player. Depending on how many views does your monitor support you should download 5-view or 9-view video. View order is also important. You should choose view order (from left to right OR from right to left) supported by your player.
|5 view alignment:||9 view alignment:|
|From left to right||From left to right||From right to left|
Conversion output format can be also specified to be a sequence of numbered views or other appropriate way.
As a result of the work the method of 3D video creating using web-cameras was developed and two versions of demo video were created (for 5-view and 9-view monitors). Video sequences are available for download (See link below).
All videos encoded by XVID codec.
3D videos were generated by MSU Stereo To Multiview Conversion algorithm developed by our laboratory.
For questions and proposition please contact us
MSU Benchmark Collection
- Video Saliency Prediction Benchmark
- Super-Resolution for Video Compression Benchmark
- Metrics Robustness Benchmark
- Video Upscalers Benchmark
- Video Deblurring Benchmark
- Video Frame Interpolation Benchmark
- HDR Video Reconstruction Benchmark
- No-Reference Video Quality Metrics Benchmark
- Full-Reference Video Quality Metrics Benchmark
- Video Alignment and Retrieval Benchmark
- Mobile Video Codecs Benchmark
- Video Super-Resolution Benchmark
- Shot Boundary Detection Benchmark
- Deinterlacer Benchmark
- The VideoMatting Project
- Video Completion
- Codecs Comparisons & Optimization
- MSU Datasets Collection
- Metrics Research
- Video Quality Measurement Tool 3D
- Video Filters
- Other Projects