Abstract: The present disclosure provides a technical solution related to processing images in image transformation by fusion. More particularly, an image of an object of an original picture may be transferred onto an image of a corresponding object in a template picture by fusion. During the transformation by fusion, the processing of fusion may be done on each pixel by using a pixel weight graph, so that the image of the object in the original picture may be better integrated into the template picture with the features of the object in the original picture maintained well in the picture processed by fusion.
Abstract: A method for efficiently populating a display is provided. The method can include identifying a point at which a world ray intersects a capture surface defined by capture points of a scene, identifying a capture point closest to the identified point, generating a motion vector based on the motion vectors for each of two directly adjacent capture points, identifying a vector in the generated motion vector at a location at which the world ray intersects an image surface, and providing a pixel value from the image data of the capture point, the pixel value corresponding to a location in the image surface at which a vector of the generated motion vector points to the location at which the world ray intersects the image surface within a threshold distance or after a specified number of iterations.
Type:
Grant
Filed:
February 15, 2019
Date of Patent:
October 12, 2021
Assignee:
Microsoft Technologv Licensing. LLC
Inventors:
Ashraf A. Michail, Yang You, Michael G. Boulton