View synthesis
Currently a study branch of Computer Science Research, aims to create new views of a specific subject starting from a number of pictures taken from given point of views.
Vision Research and Artificial Intelligence fields are involved in the definition of suitable approaches to the problem. See Computer Vision
Example problem 1: Given a number of images of a specific subject, taken from specific points with specific camera setting and orientations, try to build a synthetic image as taken from a virtual camera placed in a different point and with given settings.
Example problem 2: Two people interact through their computers, using a webcam. Try to render corrected images, as if taken from a virtual webcam positioned behind the application window. This would solve the long standing Eye contact problem which is experienced in this environment. A double illusion is perceived by the users: each of them looks at each other's face, but neither of them get the proper feeling of it.
An example application of View Synthesis is Free view point television.
See also
External links
- Mansi Sharma; Santanu Chaudhury; Brejesh Lall; (2014). Kinect-Variety Fusion: A Novel Hybrid Approach for Artifacts-Free 3DTV Content Generation. In 22nd International Conference on Pattern Recognition (ICPR), Stockholm, 2014,. doi:10.1109/ICPR.2014.395.
- http://news.bbc.co.uk/1/hi/technology/3833831.stm
- http://www.cs.wisc.edu/computer-vision/projects/interp/interp.html
- http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/FUSIELLO4/tutorial.html#x1-10001
- http://www-sop.inria.fr/robotvis/personnel/fabad/PhD/index.html
- http://www.cs.huji.ac.il/labs/vision/demos/synthesis/synthesis.html
- http://www.hpl.hp.com/research/mmsl/projects/graphics/chromaglyph/index.html