Method, apparatus, medium, and device for generating multi-angle free-respective image data
Methods, apparatuses, mediums, and devices for generating multi-angle free-respective image data are provided. The method for generating multi-angle free-perspective image data includes: acquiring multiple synchronized images, where the multiple images have different shooting angles; determining the depth data of each image based on the multiple images; and for each of the images, storing pixel data of the image in a first field and storing depth data in a second field associated with the first field. Technical solutions in the example embodiments of the present invention may improve the user experience.
1. A method, comprising:
acquiring multiple synchronized images, wherein the multiple synchronized images have different shooting angles;
determining depth data of a respective image of the multiple synchronized images based on the multiple synchronized images; and
for the respective image, storing pixel data of the respective image in a first field and storing the depth data of the respective image in a second field associated with the first field, wherein both the first field and the second field are pixel fields in a stitched image;
wherein the stitched image includes a combination of the pixel data and the depth data of the multiple synchronized images, and the stitched image is split into an image area and a depth map area, and a pixel field of the image area stores the pixel data of the multiple synchronized images, and a pixel field of the depth map area stores depth data of the multiple synchronized images;
wherein a pixel field storing the pixel data of the respective image in the image area is configured as the first field, and a pixel field storing the depth data of the respective image in the depth map area is configured as the second field; and
wherein for the respective image, the pixel data of the respective image is sequentially stored in the first field according to a preset order, and the depth data of the respective image is sequentially stored in the second field according to the preset order.
2. The method of claim 1 , wherein the depth data includes all or some of depth values in a depth value set corresponding to pixel points of the respective image on a one-to-one basis.
3. The method of claim 1 , wherein determining the depth data of the respective image includes:
storing a calculated depth value set corresponding to pixel points of the respective image on a one-to-one basis as an original depth map according to an arrangement of the pixel points of the respective image; and
down-sampling the original depth map to obtain the depth data.
4. The method of claim 1 , wherein the image area includes multiple image sub-areas, and a respective image sub-area is configured to store one of the multiple synchronized images, and a pixel field of the respective image sub-area is configured as the first field; and
wherein the depth map area includes multiple depth map sub-areas, and a respective depth map sub-area is configured to store depth data of one of the multiple synchronized images, and a pixel field of the respective depth map sub-area is configured as the second field.
5. The method of claim 4 , wherein the pixel data of the respective image is stored in the respective image sub-area in the order of an arrangement of pixel points of the respective image, and the depth data of the respective image is stored in the pixel field of the respective depth map sub-area in the order of an arrangement of pixel points of the respective image.
6. The method of claim 4 , wherein a data amount of the respective depth map sub-area is smaller than a data amount of the respective image sub-area.
7. The method of claim 4 , wherein the pixel field of the respective image sub-area stores three-channel data, and the pixel field of the respective depth map sub-area stores single-channel data.
8. The method of claim 4 , wherein the respective image sub-area stores three-channel data, and the respective depth map sub-area stores dual-channel data.
9. The method of claim 4 , further comprising:
performing padding on all or some of the image sub-areas and the depth map sub-areas.
10. The method of claim 1 , wherein the image area is a continuous area, and the depth map area is a continuous area.
11. The method of claim 1 , wherein storing the pixel data of the respective image in the first field includes: storing data obtained by reducing a resolution of the respective image in the first field.
12. The method of claim 1 , further comprising:
generating an association relationship field, wherein the association relationship field indicates an association relationship between the first field and the second field.
13. The method of claim 1 , further comprising:
calculating and storing parameter data of the respective image based on the multiple synchronized images, wherein the parameter data includes data of a shooting position and a shooting angle of the respective image.
14. The method of claim 13 , wherein the parameter data further includes internal parameter data, and the internal parameter data includes attribute data of an image capturing device.
15. The method of claim 1 , wherein the multiple synchronized images are multiple synchronized frame images obtained by decoding multiple videos.
16. An apparatus, comprising:
one or more processors; and
memory communicatively coupled to the one or more processors, the memory storing computer-executable units executable by the one or more processors, the computer-executable units including:
a synchronized image acquiring unit, configured to acquire multiple synchronized images, wherein the multiple synchronized images have different shooting angles;
a depth data determining unit, configured to determine depth data of a respective image based on the multiple images; and
a storage unit, configured to, for the respective image, store pixel data of the respective image in a first field and store the depth data of the respective image in a second field associated with the first field, wherein both the first field and the second field are pixel fields in a stitched image;
wherein the stitched image includes a combination of the pixel data and the depth data of the multiple synchronized images, and the stitched image is split into an image area and a depth map area, and a pixel field of the image area stores the pixel data of the multiple synchronized images, and a pixel field of the depth map area stores depth data of the multiple synchronized images;
wherein a pixel field storing the pixel data of the respective image in the image area is configured as the first field, and a pixel field storing the depth data of the respective image in the depth map area is configured as the second field; and
wherein for the respective image, the pixel data of the respective image is sequentially stored in the first field according to a preset order, and the depth data of the respective image is sequentially stored in the second field according to the preset order.
17. A computer-readable storage medium having computer instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform acts comprising:
acquiring multiple synchronized images, wherein the multiple synchronized images have different shooting angles;
determining depth data of a respective image of the multiple synchronized images based on the multiple synchronized images; and
for the respective image, storing pixel data of the respective image in a first field and storing the depth data of the respective image in a second field associated with the first field, wherein both the first field and the second field are pixel fields in a stitched image;
wherein the stitched image includes a combination of the pixel data and the depth data of the multiple synchronized images, and the stitched image is split into an image area and a depth map area, and a pixel field of the image area stores the pixel data of the multiple synchronized images, and a pixel field of the depth map area stores depth data of the multiple synchronized images; and
wherein a pixel field storing the pixel data of the respective image in the image area is configured as the first field, and a pixel field storing the depth data of the respective image in the depth map area is configured as the second field; and
wherein for the respective image, the pixel data of the respective image is sequentially stored in the first field according to a preset order, and the depth data of the respective image is sequentially stored in the second field according to the preset order.