Image processing method, apparatus, and storage medium

Patent metadata

Field	Value
Publication number	US-11410320-B2
Application number	US-202017028779-A
Country	US
Kind code	B2
Filing date	Sep 22, 2020
Priority date	Oct 11, 2017
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

Abstract

The present disclosure discloses an image processing method, apparatus, and a non-transitory computer readable medium. The method can includes: acquiring a three-dimensional (3D) model and original texture images of an object, wherein the original texture images are acquired by an imaging device; determining a mapping relationship between the 3D model and the original texture images of the object; determining, among the original texture images, a subset of texture images associated with a first perspective of the imaging device; splicing the subset of texture images into a spliced texture image corresponding to the first perspective; and mapping the spliced texture image to the 3D model according to the mapping relationship.

First claim

What is claimed is:

1. An image processing method, comprising:
determining a mapping relationship between a three-dimensional (3D) model and texture images of an object;
determining, among the texture images, a subset of texture images associated with a first perspective of an imaging device;
splicing the subset of texture images into a spliced texture image corresponding to the first perspective; and
mapping the spliced texture image to the 3D model according to the mapping relationship.

2. The image processing method of claim 1 , wherein determining, among the texture images, the subset of texture images associated with the first perspective of the imaging device further comprises:
acquiring a polygonal patch of the 3D model as a patch to be processed;
obtaining a normal vector of the patch to be processed;
in response to an included angle between an incident ray of the imaging device and the normal vector of the patch to be processed meeting a threshold condition, determining the included angle as the first perspective.

3. The image processing method of claim 1 , wherein splicing the subset of texture images into a spliced texture image corresponding to the first perspective further comprises:
determining an overlapping region of the texture images in the subset as a splicing region of the subset; and
texture-blending the splicing region to obtain the spliced texture image corresponding to the first perspective.

4. The image processing method of claim 3 , wherein texture-blending the splicing region to obtain the spliced texture image corresponding to the first perspective further comprises:
determining a sharpness function of the images in the subset;
determining an integrity function of the images in the subset based on a relationship between integrity of the images in the subset and an area of the splicing region; and
texture-blending the splicing region based on the sharpness function and the integrity function.

5. The image processing method of claim 1 , further comprising:
generating a spliced texture image of a second perspective of the imaging device; and
generating a texture model of the 3D model based on the spliced texture images of the first perspective and the second perspective.

6. The image processing method of claim 5 , further comprising:
performing light equalization processing on the texture model.

7. An image processing apparatus, comprising:
a memory storing a set of instructions; and
at least one processor configured to execute the set of instructions to cause the image processing apparatus to:
determine a mapping relationship between a three-dimensional (3D) model and texture images of an object;
determine, among the texture images, a subset of texture images associated with a first perspective of an imaging device;
splice the subset of texture images into a spliced texture image corresponding to the first perspective; and
map the spliced texture image to the 3D model according to the mapping relationship.

8. The image processing apparatus of claim 7 , wherein the at least one processor is further configured to execute the set of instructions to cause the image processing apparatus to:
acquire a polygonal patch of the 3D model as a patch to be processed;
obtain a normal vector of the patch to be processed;
in response to an included angle between an incident ray of the imaging device and the normal vector of the patch to be processed meeting a threshold condition, determine the included angle as the first perspective.

9. The image processing apparatus of claim 7 , wherein the at least one processor is further configured to execute the set of instructions to cause the image processing apparatus to:
determine an overlapping region of the texture images in the subset as a splicing region of the subset; and
texture-blend the splicing region to obtain the spliced texture image corresponding to the first perspective.

10. The image processing apparatus of claim 9 , wherein the at least one processor is further configured to execute the set of instructions to cause the image processing apparatus to:
determine a sharpness function of the images in the subset;
determine an integrity function of the images in the subset based on a relationship between integrity of the images in the subset and an area of the splicing region; and
texture-blend the splicing region based on the sharpness function and the integrity function.

11. The data processing apparatus of claim 7 , wherein the at least one processor is further configured to execute the set of instructions to cause the image processing apparatus to:
generate a spliced texture image of a second perspective of the imaging device; and
generate a texture model of the 3D model based on the spliced texture images of the first perspective and the second perspective.

12. The data processing apparatus of claim 11 , wherein the at least one processor is further configured to execute the set of instructions to cause the image processing apparatus to:
perform light equalization processing on the texture model.

13. A non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of a computer system to cause the computer system to perform an image processing method, the method comprising:
determining a mapping relationship between a three-dimensional (3D) model and texture images of an object;
determining, among the texture images, a subset of texture images associated with a first perspective of an imaging device;
splicing the subset of texture images into a spliced texture image corresponding to the first perspective; and
mapping the spliced texture image to the 3D model according to the mapping relationship.

14. The non-transitory computer readable medium of claim 13 , wherein determining, among the texture images, the subset of texture images associated with the first perspective of the imaging device further comprises:
acquiring a polygonal patch of the 3D model as a patch to be processed;
obtaining a normal vector of the patch to be processed;
in response to an included angle between an incident ray of the imaging device and the normal vector of the patch to be processed meeting a threshold condition, determining the included angle as the first perspective.

15. The non-transitory computer readable medium of claim 13 , wherein splicing the subset of texture images into a spliced texture image corresponding to the first perspective further comprises:
determining an overlapping region of the texture images in the subset as a splicing region of the subset; and
texture-blending the splicing region to obtain the spliced texture image corresponding to the first perspective.

16. The non-transitory computer readable medium of claim 15 , wherein texture-blending the splicing region to obtain the spliced texture image corresponding to the first perspective further comprises:
determining a sharpness function of the images in the subset;
determining an integrity function of the images in the subset based on a relationship between integrity of the images in the subset and an area of the splicing region; and
texture-blending the splicing region based on the sharpness function and the integrity function.

17. The non-transitory computer readable medium of claim 13 , wherein the set of instructions is further executable by the at least one processor of the computer system to cause the computer system to:
generate a spliced texture image of a second perspective of the imaging device; and
generate a texture

Assignees

• Alibaba Group Holding Ltd

Inventors

• Wang Bin
• Yu Jingming
• Feng Xiaoduan
• Pan Pan
• Jin Rong

Classifications

• G06T15/04 Primary

  Texture mapping · CPC title

• G06F16/5862

  using texture · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T17/00

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G06T19/003

  Navigation within 3D models or images · CPC title