Depth estimation data generating apparatus, depth estimation data generating method, and depth estimation data generating program, and pseudo three-dimensional image generating apparatus, pseudo three-dimensional image generating method, and pseudo three-dimensional image generating program

摘要

An average value, minimum value, and maximum value data detecting unit detects an average value, a minimum value, and a maximum value in one frame of a red (R) signal. A difference value calculating unit calculates a difference value by subtracting the average value from the R signal. A processing unit estimates the average value to be a level of a background image occupying a large area of a screen, and generates a signal indicating a minimum value (concavity) at the average value and a maximum value (convexity) at the maximum or minimum value as a compensated object signal. An adding unit adds the compensated object signal to a composed image of basic depth models to generate depth estimation data for generating an image in a different viewpoint from a non-3D image, the image in the different viewpoint and the non-3D image constituting the pseudo 3D image.

主权项

1. A depth estimation data generating apparatus comprising:
a generating unit which generates images of a plurality of basic depth models respectively indicating depth values of a plurality of basic scene structures; a composition ratio calculating unit which calculates a composition ratio between the images of the plurality of basic depth models by using statistics of at least some pixel values in a predetermined region in a screen of a non-three-dimensional (3D) image, so as to estimate a scene structure of the non-3D image in which depth information is neither explicitly included nor implicitly included unlike a stereo image that implicitly includes the depth information; a composing unit which generates a composed image of basic depth models by composing the images of the plurality of basic depth models generated from the generating unit according to the composition ratio; a detecting unit which receives an object signal indicating object information about concavity and convexity of a pseudo 3D image from the non-3D image, and detects an average value, a minimum value, and a maximum value in one frame or one field of the object signal; a processing unit which calculates a compensated object signal by compensating the object signal to provide a linear compensated object signal from a second maximum value to a second minimum value when the object signal changes from the minimum value to the average value and provide the linear compensated object signal from the second maximum value to the second minimum value when the object signal changes from the maximum value to the average value; and an adding unit which adds the compensated object signal to the composed image of the basic depth models composed by the composing unit to generate depth estimation data for generating an image in a different viewpoint from the non-3D image, the image in the different viewpoint and non-3D image constituting a pseudo 3D image.