Contact person: Dmitriy S. Vatolin (dmitriy@graphics.cs.msu.ru)
![picture](http://graphics.cs.msu.ru/sites/default/files/u535/video_matting/problem.png)
Main problems:
- dealing with fuzzy edges
- filling occlusion areas when extrapolating new views
Scheme of our multiview generation process
![picture](http://graphics.cs.msu.ru/sites/default/files/u535/video_matting/scheme_of_the_process.png)
Dealing with fuzzy edges
When it is necessary:
- Edges with very complicated structure (hair, fur and etc.)
- Some pixels of source image may be a mixture of background and foreground due to
- optical blur
- motion blur
- sub-pixel object shifts
- Solution: use Matting to decompose source image to background image, foreground image and transparency map
![picture](http://graphics.cs.msu.ru/sites/default/files/u535/video_matting/matting.jpg)
Filling occlusion areas
When extrapolating new views source images don't contain all necessary information
to fill occlusions on edges of depth map
Solution:
- Temporal inpainting ? take missing information from other frames
- Spatial inpainting ? use current frame to generate missing information
Spatial inpainting techniques comparison
![picture](http://graphics.cs.msu.ru/sites/default/files/u535/video_matting/comparison.jpg)
![picture](http://graphics.cs.msu.ru/sites/default/files/u535/video_matting/comparison_ssim.png)
Team
Acknowledgements
This work is partially supported by the Intel/Cisco Video-Aware Wireless Network (VAWN) Program