Stereoscopic image generation method and stereoscopic image generation system

摘要

A stereoscopic image generation method and a stereoscopic image generation system that can generate, from an original image, a stereoscopic image that allows the viewer to perceive a natural stereoscopic effect are provided. The method includes a characteristic information acquisition step of acquiring characteristic information for each of pixels, a depth information generation step of generating depth information for each of the pixels on the basis of the characteristic information, and a stereoscopic image generation step of generating a stereoscopic image on the basis of the pieces of depth information.

主权项

1. A stereoscopic image generation method comprising:
a characteristic information acquisition step of acquiring characteristic information for each of pixels constituting an original image; a region dividing step of dividing the original image into a plurality of regions, a depth information generation step of generating depth information for each of the pixels on the basis of the characteristic information; and a stereoscopic image generation step of generating a stereoscopic image in which positions of the respective pixels are changed on the basis of the pieces of depth information, wherein the depth information generation step includes
an edge setting step of setting an edge for each of pairs of pixels extracted from the original image,a weight information setting step of setting weight information for each of the edges on the basis of the characteristic information,a start area selection step of selecting a start area from the pixels,a path information setting step of computing a path connecting a pair of pixels by the edge from the start area to each of the pixels, acquiring a sum of pieces of weight information on each of the paths and setting a path information for each of the pixels on the basis of the sum of pieces of weight information on the path,a depth determination step of setting the depth information for each of the pixels on the basis of the path information for the pixel, whereinin the edge setting step, the edge is set for a pair of adjacent pixels and/or a pair of separated or isolated pixels,in the start area selection step, the start area is selected as a common start point of the paths,in the start area selection step the start area is selected independently for each of the plurality of regions, andin the path information setting step, the path is computed independently for each of the plurality of regions, and the path information is set for each of the pixels.