Image processing apparatus and image processing method
There is provided an image processing apparatus and an image processing method that are capable of improving the accuracy of a depth image of a 3D model. A depth image generation unit generates a depth image of a plurality of viewpoints for each object included in a 3D model. The present disclosure is applicable to, for example, an encoding device or the like configured to generate a color image and a depth image of each object of each of a plurality of viewpoints on the basis of 3D data of a 3D model, generate an encoded stream by encoding the images, and generate object range information indicating the range of each object.
1. An image processing apparatus comprising:
circuitry configured to
divide a 3D model into one or more objects,
generate depth images from a plurality of viewpoints for a plurality of objects based on the divided 3D model for each object,
generate object range information with respect to each viewpoint based on the generated depth images of each viewpoint for each object of the plurality of objects, the object range information indicating a two-dimensional position on the depth images and depth on the depth images, and
transmit the generated depth images from the plurality of viewpoints and the generated object range information for the plurality of objects to an external decoding device,
wherein the generated object range information includes a minimum value and a maximum value in each dimension of at least two dimensions registered in association with each object with respect to each viewpoint.
2. The image processing apparatus according to claim 1 , wherein the circuitry generates the object range information indicating a range of each respective object on the depth image and a range of a distance between each viewpoint corresponding to the depth image and the respective object in a depth direction.
3. The image processing apparatus according to claim 1 , wherein the circuitry generates the object range information indicating a range of each object on a 3D coordinate system.
4. The image processing apparatus according to claim 1 , wherein the circuitry is further configured to determine the plurality of viewpoints on a basis of the 3D model, and
wherein the 3D model comprises a temporally sequential 3D model with the plurality of viewpoints determined so that temporal change of a position of a predetermined object of the plurality of objects on the depth image of each viewpoint decreases.
5. The image processing apparatus according to claim 1 , wherein the circuitry is further configured to determine, for each object, the plurality of viewpoints on a basis of a selected temporally sequential object of the plurality of objects so that temporal change of the position of the selected temporally sequential object on the depth image of each viewpoint decreases.
6. The image processing apparatus according to claim 1 , wherein the generated object range information includes the minimum value and the maximum value in each dimension of at least three dimensions registered in association with each object based on the plurality of viewpoints.
7. The image processing apparatus according to claim 1 , wherein the circuitry is further configured to generate color images of each viewpoint of the plurality of viewpoints for each object of the plurality of objects based on the divided 3D model for each object.
8. An image processing method comprising:
dividing a 3D model into one or more objects;
generating, by an image processing apparatus, depth images from a plurality of viewpoints for a plurality of objects based on the divided 3D model for each object;
generating object range information with respect to each viewpoint based on the generated depth images of each viewpoint for each object of the plurality of objects, the object range information indicating a two-dimensional position on the depth images and depth on the depth images; and
transmitting the generated depth images from the plurality of viewpoints and the generated object range information for the plurality of objects to an external decoding device,
wherein the generated object range information includes a minimum value and a maximum value in each dimension of at least two dimensions registered in association with each object with respect to each viewpoint.
9. An image processing apparatus comprising:
circuitry configured to
decide a three-dimensional region for a plurality of objects based on virtual viewpoint information,
decide object range information for each object of the plurality of objects, the object range information indicating a two-dimensional position on the depth images and depth on the depth images, and
reconstruct the plurality of objects, in the decided three-dimensional region, based on the virtual viewpoint information, depth images from a plurality of viewpoints for the plurality of objects, and color images for the plurality of objects,
wherein the decided object range information includes a minimum value and a maximum value in each dimension of at least two dimensions registered in association with each object with respect to each viewpoint.
10. The image processing apparatus according to claim 9 , wherein the three-dimensional region is decided based on a range of each respective object on the depth image and a range of a distance between each viewpoint corresponding to the depth image and the respective object in a depth direction.
11. The image processing apparatus according to claim 9 , wherein the three-dimensional region is decided based on a range of each object on a 3D coordinate system.
12. The image processing apparatus according to claim 9 , wherein the plurality of viewpoints are determined on a basis of a 3D model of the plurality of objects, and
wherein the 3D model comprises a temporally sequential 3D model with the plurality of viewpoints determined so that temporal change of a position of a predetermined object of the plurality of objects included in the 3D model on the depth image of each viewpoint decreases.
13. The image processing apparatus according to claim 9 , wherein the plurality of viewpoints are determined on a basis of a selected temporally sequential object of the plurality of objects so that temporal change of the position of the selected temporally sequential object on the depth image of each viewpoint decreases.
14. The image processing apparatus according to claim 9 , wherein the circuitry separately generates each object of the plurality of objects.
15. An image processing method comprising:
deciding a three-dimensional region for a plurality of objects based on virtual viewpoint information;
deciding object range information for each object of the plurality of objects, the object range information indicating a two-dimensional position on depth images and depth on the depth images; and
reconstructing the plurality of objects, in the decided three-dimensional region, based on the virtual viewpoint information, the depth images from a plurality of viewpoints for the plurality of objects, and color images for the plurality of objects,
wherein the decided object range information includes a minimum value and a maximum value in each dimension of at least two dimensions registered in association with each object with respect to each viewpoint.