US 8,078,006 B1 · Minimal artifact image sequence depth enhancement system and method

Abstract

Motion picture scenes to be colorized/depth enhanced (2D→3D) are broken into separate elements, backgrounds/sets or motion/onscreen-action. Background and motion elements are combined into composite frame which becomes a visual reference database that includes data for all frame offsets used later for the computer controlled application of masks within a sequence of frames. Masks are applied to subsequent frames of motion objects based on various differentiating image processing methods, including automated mask fitting/reshaping. Colors and/or depths are automatically applied to masks throughout a scene from the composite background and to motion objects. Areas never exposed by motion or foreground objects in a series of images may be partially or fully realistically drawn or rendered and applied to the occluded areas of the background and then automatically applied throughout the images to generate of minimal artifact or artifact-free secondary viewpoints when translating foreground objects horizontally during 2D→3D conversion.

Claims14

Dependent claims

A method of creating a visual reference database comprising:

associating a plurality of images comprising common background elements;
obtaining a composite background comprising said plurality of images wherein said composite background excludes a set of motion objects that move in said plurality of images in relation to said common background elements;
associating a first mask with a motion object selected from said set of motion objects in a first image selected from said plurality of images;
accessing a mask value associated with said first mask in said first image wherein said mask value is stored in a visual reference database;
accessing a camera value associated with said first image wherein said camera value is stored in said visual reference database;
copying said mask value associated with said first mask to create a second mask value associated with a second mask and further associated with a second image selected from said plurality of images;
moving said second mask value to a location of said motion object in said second image;
reshaping said second mask value automatically to fit said motion object in said second image based on said camera value using a computer;
and,
storing said second mask value in said visual reference database.

7 more elements

A system configured to modify a set of time ordered digital images comprising

a visual reference database;
a computer configured to
associate a plurality of images comprising common background elements;
obtain a composite background comprising said plurality of images wherein said composite background excludes a set of motion objects that move in said plurality of images in relation to said common background elements;
associate a first mask with a motion object selected from said set of motion objects in a first image selected from said plurality of images;
access a mask value associated with said first mask in said first image wherein said mask value is stored in said visual reference database;
access a camera value associated with said first image wherein said camera value is stored in said visual reference database;
copy said mask value associated with said first mask to create a second mask value associated with a second mask and further associated with a second image selected from said plurality of images;
move said second mask value to a location of said motion object in said second image;
reshape said second mask value to fit said motion object in said second image based on said camera value;
and,
store said second mask value in said visual reference database.

9 more elements

Dependencies are inferred from the claim text.

Minimal artifact image sequence depth enhancement system and method

Life of this patent

Minimal artifact image sequence depth enhancement system and method

Life of this patent

Abstract

Claims14