Image processing device, image processing method, and image processing program

An image processing method comprising:

• detecting a degree of congruence of each of a plurality of scenes with respect to an input image made of a two-dimensional image, by a congruence degree detecting unit configured to detect a degree of congruence of each of a plurality of scenes with respect to the input image made of the two-dimensional image;
• generating, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, by a depth image generating unit configured to generate, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes;
• blending the depth images, which are generated by performing the depth image generating step and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, by a blending unit configured to blend the depth images, which are generated by the depth image generating unit and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image;
• and
• generating a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image which are generated by shifting each of pixels of the input image using the blended depth image, by a three-dimensional image generating unit configured to generate a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image which are generated by shifting each of pixels of the input image using the blended depth image.

A non-transitory computer-readable medium having embodied thereon a program, which when executed by a processor of an image processing device causes the processor to perform a method to execute processing, wherein the image processing device includes:

• a congruence degree detecting unit configured to detect a degree of congruence of each of a plurality of scenes with respect to an input image made of a two-dimensional image, a depth image generating unit configured to generate, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, a blending unit configured to blend the depth images, which are generated by the depth image generating unit and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, and a three-dimensional image generating unit configured to generate a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image which are generated by shifting each of pixels of the input image using the blended depth image, and wherein the processing includes detecting, by the congruence degree detecting unit, a degree of congruence of each of a plurality of scenes with respect to the input image made of the two-dimensional image, generating, by the depth image generating unit, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, blending, by the blending unit, the depth images, which are generated by performing the depth image generating step and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, and generating, by the three-dimensional image generating unit, a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image which are generated by shifting each of pixels of the input image using the blended depth image.