Information processing device, video processing method, and program
AssigneeSony Group Corporation
InventorHisako SUGANO
Life of this patent
Estimating the term…
Abstract
An information processing device includes a video processing unit that performs, on a captured video obtained by capturing a display video of a display device and an object, video processing of a display video area determined using mask information for separating a display video and an object video in the captured video, or video processing of an object video area determined using the mask information.
Claims20
An information processing method, executed by an information processing device, the method comprising:
- performing, on a captured image obtained by capturing a display image displayed on a display device and an object separate from the display device, at least one of
- processing of a display image area determined using mask information for separating the captured image into the display image area and an object image area in the captured image, or
- processing of an object image area determined using the mask information,
- wherein the display image is rendered using three-dimensional (3D) data,
- wherein the processing includes at least one of
- replacing the display image in the display image area with a first image separately generated based on the 3D data, or
- compositing the object image in the object image area with a second image separately generated based on the 3D data, and
- wherein an area of the second image corresponds to the display image area.
An information processing method, executed by an information processing device, the method comprising:
- performing, on a captured image obtained by capturing a display image displayed on a display device and an object separate from the display device, at least one of
- replacing the display image in a display image area of the captured image with a first image separately generated based on three-dimensional (3D) data, the display image being rendered using the 3D data, or
- compositing an object image in an object image area of the captured image with a second image separately generated based on the 3D data,
- wherein an area of the second image corresponds to the display image area, and
- wherein the display image area and the object image area are determined using mask information for separating the display image area and the object image area in the captured image.
A non-transitory computer-readable storage medium having embodied thereon a program, which when executed by a computer causes the computer to execute a method, the method comprising:
- performing, on a captured image obtained by capturing a display image displayed on a display device and an object separate from the display device, at least one of
- replacing the display image in a display image area of the captured image with a first image separately generated based on three-dimensional (3D) data, the display image being rendered using the 3D data, or
- compositing an object image in an object image area of the captured image with a second image separately generated based on the 3D data,
- wherein an area of the second image corresponds to the display image area, and
- wherein the display image area and the object image area are determined using mask information for separating the display image area and the object image area in the captured image.
Dependencies are inferred from the claim text.