Image processing apparatus, image processing method, and storage medium for generating composite image using 2D image and 3DCG
To make it possible to obtain a natural image in which a foreground object included in a two-dimensional image and a background object included in a three-dimensional computer graphics space are in harmony with each other. A two-dimensional image, corresponding to a specific viewpoint, including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image are obtained. Then, an image including the foreground object and a background object is generated by arranging a screen based on the position and shape data in a computer graphics space including the background object and projecting the image of the foreground object included in the two-dimensional image.
1. An image processing apparatus comprising:
one or more memories that store instructions; and
one or more processors that execute the instructions to perform:
obtaining a two-dimensional image, corresponding to a specific viewpoint and including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image; and
generating an image including the foreground object and a background object by arranging a screen based on the position and shape data in a computer graphics space including the background object, and by projecting the image of the foreground object included in the two-dimensional image onto the screen based on the parameter,
wherein the screen is a three-dimensional shape and a transparent bounding box.
2. The image processing apparatus according to claim 1 , wherein
the position and shape data is data describing a three-dimensional position of each vertex of a rectangular parallelepiped circumscribing the foreground object and a length of each side of the rectangular parallelepiped.
3. The image processing apparatus according to claim 1 , wherein
in the generating an image, by forming a pseudo shadow of the foreground object based on the position and shape data in a three-dimensional space of the computer graphics, an image including the foreground object and the background object is generated.
4. The image processing apparatus according to claim 3 , wherein
the pseudo shadow is a translucent black or gray ellipse.
5. The image processing apparatus according to claim 1 , wherein
the two-dimensional image corresponding to the specific viewpoint is a frame constituting a moving image and
the one or more processors further execute the instructions to perform generating position and shape data synchronized with each frame of the moving image in a case where an obtaining period of the position and shape data and an obtaining period of a frame constituting the moving image are different.
6. The image processing apparatus according to claim 1 , wherein
the two-dimensional image corresponding to the specific viewpoint is a captured image obtained by an imaging device and
the parameter is an image capturing parameter representing a condition at the time of capturing the object by the imaging device.
7. The image processing apparatus according to claim 6 , wherein
the image of the foreground object is an image obtained by performing chroma key processing for the captured image.
8. The image processing apparatus according to claim 1 , wherein
the two-dimensional image corresponding to the specific viewpoint is a virtual viewpoint image generated based on a plurality of captured images obtained by capturing the object from a plurality of viewpoints by an imaging device and representing an appearance from a virtual viewpoint different from the plurality of viewpoints and
the parameter is a virtual viewpoint parameter representing a condition at the time of generating the virtual viewpoint image.
9. The image processing apparatus according to claim 8 , wherein
in the obtaining, position and shape data of the object is obtained based on data representing a three-dimensional shape of the object generated by using the plurality of captured images.
10. An image processing apparatus comprising:
one or more memories that store instructions; and
one or more processors that execute the instructions to perform:
obtaining a two-dimensional image corresponding to a specific viewpoint and including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image; and
generating an image including the foreground object and a background object by arranging a screen based on the position and shape data in a computer graphics space including the background object, and by projecting the image of the foreground object included in the two-dimensional image onto the screen based on the parameter,
wherein in the generating an image, by rendering that determines a color of each pixel based on a distance from a viewpoint that is set based on the parameter to each foreground object, an image including the foreground object and the background object is generated.
11. The image processing apparatus according to claim 10 , wherein
in the generating an image:
a condition at the time of performing the projection is set in accordance with a condition at the time of obtaining the two-dimensional image, which is specified by the parameter.
12. The image processing apparatus according to claim 10 , wherein the two-dimensional image corresponding to the specific viewpoint is a frame constituting a moving image, and in the obtaining, the position and shape data is obtained at timing synchronized with a fame constituting the moving image.
13. The image processing apparatus according to claim 10 , wherein
the two-dimensional image corresponding to the specific viewpoint is a virtual viewpoint image generated based on a plurality of captured images obtained by capturing the object from a plurality of viewpoints by an imaging device and representing an appearance from a virtual viewpoint different from the plurality of viewpoints, and
the parameter is a virtual viewpoint parameter representing a condition at the time of generating the virtual viewpoint image.
14. The image processing apparatus according to claim 13 , wherein
in the obtaining, position and shape data of the object is obtained based on data representing a three-dimensional shape of the object generated by using the plurality of captured images.
15. An image processing method comprising:
obtaining a two-dimensional image, corresponding to a specific viewpoint and including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image; and
generating an image including the foreground object and a background object by arranging a screen based on the position and shape data in a computer graphics space including the background object, and by projecting the image of the foreground object included in the two-dimensional image onto the screen based on the parameter,
wherein the screen is a three-dimensional shape and a transparent bounding box.
16. A non-transitory computer readable storage medium storing a program for causing a computer to perform an image processing method comprising:
obtaining a two-dimensional image, corresponding to a specific viewpoint and including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image; and
generating an image including the foreground object and a background object by arranging a screen based on the position and shape data in a computer graphics space including the background object, and by projecting the image of the foreground object included in the two-dimensional image onto the screen based on the parameter,
wherein the screen is a three-dimensional shape and a transparent bounding box.
17. An image processing method comprising:
obtaining a two-dimensional image corresponding to a specific viewpoint and including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image; and
generating an image including the foreground object and a background object by arranging a screen based on the position and shape data in a computer graphics space including the background object, and by projecting the image of the foreground object included in the two-dimensional image onto the screen based on the parameter,
wherein in the generating an image, by rendering that determines a color of each pixel based on a distance from a viewpoint that is set based on the parameter to each foreground object, an image including the foreground object and the background object is generated.
18. A non-transitory computer readable storage medium storing a program for causing a computer to perform an image processing method comprising:
obtaining a two-dimensional image corresponding to a specific viewpoint and including a foreground object, a parameter specifying a condition at the time of obtaining the two-dimensional image, and position and shape data representing a three-dimensional position and a shape of the foreground object included in the two-dimensional image; and
generating an image including the foreground object and a background object by arranging a screen based on the position and shape data in a computer graphics space including the background object, and by projecting the image of the foreground object included in the two-dimensional image onto the screen based on the parameter,
wherein in the generating an image, by rendering that determines a color of each pixel based on a distance from a viewpoint that is set based on the parameter to each foreground object, an image including the foreground object and the background object is generated.