Image processing system, image processing apparatus, image processing method, and program

1. An image processing system for generating a virtual viewpoint image, comprising:

one or more hardware processors; and

one or more memories storing one or more programs configured to be executed by the one or more hardware processors, the one or more programs including instructions for:

acquiring viewpoint information indicating a virtual viewpoint;

acquiring, based on a plurality of captured images acquired by shooting a target region by a plurality of imaging apparatuses from a plurality of directions, a plurality of background images not including a predetermined object in the target region and an image of the predetermined object;

extracting a partial image to be used to generate the virtual viewpoint image from a background image included in the plurality of background images; and

generating the virtual viewpoint image based on the partial image, the image of the predetermined object and the viewpoint information,

wherein a value of a pixel in the virtual viewpoint image corresponding to a specific position in the target region is determined based on two or more partial images which include images at the specific position in the target region and which are extracted from two or more background images included in the acquired plurality of background images.

2. The image processing system according to claim 1 ,

wherein the partial image is extracted such that a predetermined number of partial images including an image of the same region in the target region are present in a plurality of partial images extracted from the background images.

3. The image processing system according to claim 1 , wherein the one or more programs further include instructions for

determining a region which is in a background image and which is extracted as a partial image,

wherein the partial image depending on the determination is extracted.

4. The image processing system according to claim 3 ,

wherein a region which is in a background image acquired based on shooting by a first imaging apparatus among the imaging apparatuses and which is extracted as a partial image is determined based on a state of a second imaging apparatus different from the first imaging apparatus among the imaging apparatuses.

5. The image processing system according to claim 4 ,

wherein the state of the second imaging apparatus includes at least any of position, orientation, direction, and lens focal length of the second imaging apparatus.

6. The image processing system according to claim 3 ,

wherein a region to be extracted as a partial image is determined based on at least any of 3D shape data corresponding to the target region and viewpoint information acquired by the information acquisition unit.

7. The image processing system according to claim 3 , wherein the one or more programs further include instructions for

acquiring information on a state of a light projected on the target region,

wherein a region to be extracted as a partial image is determined based on the information on a state of a light projected on the target region.

8. The image processing system according to claim 1 ,

wherein one or more partial images are selected out of the two or more partial images based on values of pixels corresponding to the specific position in the two or more partial images, and a value of a pixel corresponding to the specific position in the virtual viewpoint image is determined based on values of pixels corresponding to the specific position in the one or more selected partial images.

9. The image processing system according to claim 8 ,

wherein when a difference between a value of a pixel corresponding to the specific position in a first partial image out of the two or more partial images and a value of a pixel corresponding to the specific position in a second partial image out of the two or more partial images is less than a threshold, the first partial image and the second partial image are determined.

10. The image processing system according to claim 8 ,

wherein when a plurality of partial images are selected from the two or more partial images, an average value of values of pixels corresponding to the specific position in the selected partial images is determined as a value of a pixel corresponding to the specific position in the virtual viewpoint image.

11. The image processing system according to claim 1 , wherein the one or more programs further include instructions for

transmitting the partial image and the image of the predetermined object to a storage device,

wherein the generation unit generates the virtual viewpoint image based on the partial image and the image of the predetermined object stored in the storage device.

12. The image processing system according to claim 11 , wherein the one or more programs further include instructions for

determining a region which is in a background image acquired based on shooting by an imaging apparatus among the imaging apparatuses and which is extracted as a partial image based on other one or more partial images which has been transmitted and is stored in the storage device.

13. An image processing method for generating a virtual viewpoint image, comprising:

acquiring viewpoint information indicating a virtual viewpoint;

acquiring, based on a plurality of captured images acquired by shooting a target region by a plurality of imaging apparatuses from a plurality of directions, a plurality of background images not including a predetermined object in the target region and an image of the predetermined object;

extracting a partial image to be used to generate the virtual viewpoint image from a background image included in the plurality of background images; and

generating the virtual viewpoint image based on the partial image, the image of the predetermined object, and the viewpoint information,

wherein a value of a pixel in the virtual viewpoint image corresponding to a specific position in the target region is determined based on two or more partial images which include images at the specific position in the target region and which are extracted from two or more background images included in the acquired plurality of background images.

14. A non-transitory storage therein a program for causing a computer to perform an image processing method, the method comprising:

acquiring viewpoint information indicating a virtual viewpoint;

acquiring, based on a plurality of captured images acquired by shooting a target region by a plurality of imaging apparatuses from a plurality of directions, a plurality of background images not including a predetermined object in the target region and an image of the predetermined object;

extracting a partial image to be used to generate the virtual viewpoint image from a background image included in the plurality of background images; and

generating the virtual viewpoint image based on the partial image, the image of the predetermined object, and the viewpoint information,

wherein a value of a pixel in the virtual viewpoint image corresponding to a specific position in the target region is determined based on two or more partial images which include images at the specific position in the target region and which are extracted from two or more background images included in the acquired plurality of background images.