Generating 3D video from standard 2D compressed video

A new algorithm for generating 3D video from standard compressed 2-D video, using a method for extraction of motion vectors. The method allows the synthesis of dense depth maps for 3D video generation and display.
The Need The method uses inherent motion of the scene to extract enough information to generate 3D images from standard 2D sequences. The novelty of the invention is that it uses standard video encoders to extract depth maps for 3D visualization in real-time. This method does not require any changes to standard encoder hardware and very little to the decoding hardware (necessary for 3D synthesis). For displaying purposes, artificial stereo pair frames are generated from initial frames and corresponding depth maps. These stereo pairs can then be used for 3-D display when stereoscopic displays of any type are available.
Potential Applications This technique can bring major advantages to applications as wide as molecular modeling, photogrammetry, flight simulation, CAD, visualization of multidimensional data, medical imaging, tele-operations such as remote vehicle piloting and remote surgery, and stereolithography. In computer graphics, the improvements in speed, resolution, and economy make interactive stereo an important capability. True 3D is rapidly becoming an important part of computer graphics, visualization, virtual-reality systems, and computer gaming.
Patent Provisional partent has been submitted Tech Transfer Officer Mr. Larry Loev Office: +972-3-6406544 Fax: +972-3-6406675 Mail: [email protected]

Inventor(s): Leonid Yaroslavsky

Type of Offer: Licensing



« More Engineering Patents

---