Rapid workflow system and method for image sequence depth enhancement

摘要

Movies to be colorized/depth enhanced (2D→3D) are broken into 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/depths are automatically applied with masks throughout a scene from the composite background and to motion objects. Areas never exposed by motion or foreground objects may be partially or fully realistically drawn/rendered/applied to the occluded areas and applied throughout the images to generate artifact-free secondary viewpoints during 2D→3D conversion. Iterative workflow is eliminated for simple artifact correction through real-time manipulation of images to avoid re-rendering of images and associated delays of sending work product to other workgroups for correction.

主权项

1. A system configured to modify a set of time ordered digital images comprising at least one computer configured to:
obtain a source image and at least one mask associated with a region in said source image; obtain a depth map or translation values associated with said at least one mask of said source image; obtain a render of a left viewpoint image of said source image created with ray tracing to a left virtual camera; obtain a render of a right viewpoint image of said source image created with ray tracing to a right virtual camera; modify said at least one mask or an area next to said at least one mask where missing background information is located or said depth map or said translation values or any combination thereof to create at least one modified mask or modified missing background information or modified depth map or modified translation values or any combination thereof; and, update said left viewpoint image and said right viewpoint image based on said at least one modified mask or said modified depth map or said modified translation values or said any combination thereof without another said ray tracing to said left virtual camera and without said ray tracing to said right virtual camera.