Back to results
US 12,598,266 B2Granted
Image processing apparatus, image processing method, and storage medium
AssigneeCanon Kabushiki Kaisha
InventorMasahiro Handa
Life of this patent
Estimating the term…
Abstract
An object is to make it possible to provide an appropriate image. A background combined image that takes, as a foreground, an image corresponding to a virtual viewpoint that is set in an image capturing space and a background combined image that takes, as a foreground, part of a captured image captured from a specific viewpoint among a plurality of captured images are generated. Then, the configuration is designed so that it is possible to selectively output one of the background combined images.
Claims13
An image processing apparatus comprising:
- one or more memories storing instructions;
- and
- one or more processors executing the instructions to:
- generate a foreground clip image by clipping a captured area of a foreground object from a captured image obtained by a specific imaging device performing image capturing;
- obtain foreground shape data that is generated based on a plurality of captured images obtained by a plurality of imaging devices that perform image capturing, the foreground shape data indicating a three-dimensional shape of the foreground object;
- generate a virtual viewpoint image representing an appearance of the foreground object from a virtual viewpoint in a virtual space based on the foreground shape data;
- generate a background image, based on pre-prepared background shape data indicating a three-dimensional shape of a background object, the background image representing an appearance of the background object from a viewpoint corresponding to the specific imaging device in the virtual space;
- and
- selectively output at least one of a first image and a second image,
- wherein the first image is an image generated by combining the foreground image and the background image and then resizing the combined image, the foreground shape data is not used for the generation of the first image, and
- wherein the second image is an image generated based on the virtual viewpoint image and the background image.
8 more elements
An image processing method comprising the steps of:
- generating a foreground clip image by clipping a captured area of a foreground object from a captured image obtained by a specific imaging device performing image capturing;
- obtaining foreground shape data that is generated based on a plurality of captured images obtained by a plurality of imaging devices that perform image capturing, the foreground shape data indicating a three-dimensional shape of the foreground object;
- generating a virtual viewpoint image representing an appearance of the foreground object from a virtual viewpoint in a virtual space based on the foreground shape data;
- generating a background image, based on pre-prepared background shape data indicating a three-dimensional shape of a background object, the background image representing an appearance of the background object from a viewpoint corresponding to the specific imaging device in the virtual space;
- selectively outputting at least one of a first image and a second image,
- wherein the first image is an image generated by combining the foreground image and the background image and then resizing the combined image, the foreground shape data is not used for the generation of the first image, and
- wherein the second image is an image generated based on the virtual viewpoint image and the background image.
4 more elements
A non-transitory computer readable storage medium storing a program for causing a computer to perform an image processing method comprising the steps of:
- generating a foreground clip image by clipping a captured area of a foreground object from a captured image obtained by a specific imaging device performing image capturing;
- obtaining foreground shape data that is generated based on a plurality of captured images obtained by a plurality of imaging devices that perform image capturing, the foreground shape data indicating a three-dimensional shape of the foreground object;
- generating a virtual viewpoint image representing an appearance of the foreground object from a virtual viewpoint in a virtual space based on the foreground shape data;
- generating a background image, based on pre-prepared background shape data indicating a three-dimensional shape of a background object, the background image representing an appearance of the background object from a viewpoint corresponding to the specific imaging device in the virtual space;
- selectively outputting at least one of a first image and a second image,
- wherein the first image is an image generated by combining the foreground image and the background image and then resizing the combined image, the foreground shape data is not used for the generation of the first image, and
- wherein the second image is an image generated based on the virtual viewpoint image and the background image.
4 more elements
Dependencies are inferred from the claim text.