Method and apparatus for monoscopic to stereoscopic image conversion
First Claim
Patent Images
1. A method for converting a monoscopic image comprising a first perspective to a stereoscopic image comprising said first perspective and a second perspective, said monoscopic image having at least one foreground object and at least one background object, said method comprising the steps of:
- identifying at least one object in said monoscopic image;
outlining said at least one object to generate a first vector outline;
endowing said at least one object with depth information;
generating a second vector outline for said at least one object based on said depth information;
if said at least one object is determined to be said background object relative to said at least one foreground object and said at least one object overlaps said at least one foreground object, clipping said second vector outline to generate a clipped vector outline; and
generating said second perspective by image warping said at least one object.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and apparatus for converting a monoscopic image with one perspective to a stereoscopic image with two perspectives is provided. A foreground object is identified and outlined. The depth of the object is endowed with depth information. The second perspective is generated by image warping. Alternate embodiments comprising additional features, such as removing redundant frames, which reduce the necessary computation are also provided.
132 Citations
8 Claims
-
1. A method for converting a monoscopic image comprising a first perspective to a stereoscopic image comprising said first perspective and a second perspective, said monoscopic image having at least one foreground object and at least one background object, said method comprising the steps of:
-
identifying at least one object in said monoscopic image; outlining said at least one object to generate a first vector outline; endowing said at least one object with depth information; generating a second vector outline for said at least one object based on said depth information; if said at least one object is determined to be said background object relative to said at least one foreground object and said at least one object overlaps said at least one foreground object, clipping said second vector outline to generate a clipped vector outline; and generating said second perspective by image warping said at least one object. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
Specification