Method and apparatus for rendering virtual avatar, electronic device and storage medium

Patent metadata

Field	Value
Publication number	US-2025316040-A1
Application number	US-202318869808-A
Country	US
Kind code	A1
Filing date	May 22, 2023
Priority date	May 27, 2022
Publication date	Oct 9, 2025
Grant date	—

Abstract

The embodiment of the disclosure discloses a method and apparatus for rendering a virtual avatar, an electronic device and a storage medium, and the method includes: segmenting a target image to obtain at least one first object and second objects respectively corresponding to each first object; the at least one first object respectively corresponding to at least one pre-constructed first spatial building block avatar; constructing, based on a mapping relationship between the at least one first object and the at least one first spatial building block avatar respectively corresponding to the at least one first object, second spatial building block avatars of second objects respectively corresponding to each first object; and rendering each of the first spatial building block avatars and each of the second spatial building block avatars.

First claim

1 - 10 . (canceled)

11 . A method for rendering a virtual avatar, comprising:
segmenting a target image to obtain at least one first object and second objects respectively corresponding to each first object; the at least one first object respectively corresponding to at least one pre-constructed first spatial building block avatar; constructing, based on a mapping relationship between the at least one first object and the at least one first spatial building block avatar respectively corresponding to the at least one first object, second spatial building block avatars of second objects respectively corresponding to each first object; and rendering each of the first spatial building block avatars and each of the second spatial building block avatars.

12 . The method of claim 11 , wherein constructing, based on the mapping relationship between the at least one first object and the at least one first spatial building block avatar respectively corresponding to the at least one first object, the second spatial building block avatars of the second objects respectively corresponding to each first object comprises:
for each of the first objects, determining a sliding window and a step size based on a mapping relationship between a pixel size of the first object and the number of building blocks in the first spatial building block avatar corresponding to the first object; determining a grid graph of a second object by sliding on the second object corresponding to the first object using the sliding window and the step size; and constructing the second spatial building block avatar of the second object based on the grid graph.

13 . The method of claim 11 , wherein rendering each of the first spatial building block avatars and each of the second spatial building block avatars comprises:
dynamically building building blocks in each of the first spatial building block avatars and building blocks in each of the second spatial building block avatars based on a predetermined building sequence.

14 . The method of claim 12 , wherein the method further comprises: after determining the grid graphs of the second object,
determining, based on a position relationship between the second object and the corresponding first object, a to-be-constructed second spatial building block avatar corresponding to the grid graph, and a position relationship with the corresponding first spatial building block avatar; constructing and rendering the second spatial building block avatar comprises: determining a current to-be-built building block based on a predetermined building sequence and a position relationship between the to-be-constructed second spatial building block avatar and the corresponding first spatial building block avatar; in response to the current to-be-built building block belonging to the second spatial building block avatar, constructing and rendering the building block.

15 . The method of claim 13 , wherein the method further comprises: in a process of the dynamic building,
rotating and presenting the process of the dynamic building based on a predetermined rotation parameter.

16 . The method of claim 11 , wherein the method further comprises: after obtaining the at least one first object and the second objects respectively corresponding to each first object,
determining color information of the at least one first object and color information of the second objects respectively corresponding to each first object; rendering each of the first spatial building block avatars and each of the second spatial building block avatars comprises: rendering each of the first spatial building block avatars and each of the second spatial building block avatars based on the color information of the at least one first object and the color information of the second object respectively corresponding to each first object.

17 . The method of claim 11 , wherein the target image comprises a whole-body image, and the second object comprises a clothing object,
the method further comprises: after obtaining the second objects respectively corresponding to each first object, determining at least one of the following attribute information of the clothing object: type information and pattern information; and rendering the second spatial building block avatar comprises: rendering the second spatial building block avatar corresponding to the clothing object based on the attribute information of the clothing object.

18 . An electronic device, comprising:
one or more processors; a storage device, configured to store at least one program, when executed by the at least one processor, the at least one program causes the at least one processor to implement a method for rendering a virtual avatar, comprising: segmenting a target image to obtain at least one first object and second objects respectively corresponding to each first object; the at least one first object respectively corresponding to at least one pre-constructed first spatial building block avatar; constructing, based on a mapping relationship between the at least one first object and the at least one first spatial building block avatar respectively corresponding to the at least one first object, second spatial building block avatars of second objects respectively corresponding to each first object; and rendering each of the first spatial building block avatars and each of the second spatial building block avatars.

19 . The device of claim 18 , wherein constructing, based on the mapping relationship between the at least one first object and the at least one first spatial building block avatar respectively corresponding to the at least one first object, the second spatial building block avatars of the second objects respectively corresponding to each first object comprises:
for each of the first objects, determining a sliding window and a step size based on a mapping relationship between a pixel size of the first object and the number of building blocks in the first spatial building block avatar corresponding to the first object; determining a grid graph of a second object by sliding on the second object corresponding to the first object using the sliding window and the step size; and constructing the second spatial building block avatar of the second object based on the grid graph.

20 . The device of claim 18 , wherein rendering each of the first spatial building block avatars and each of the second spatial building block avatars comprises:
dynamically building building blocks in each of the first spatial building block avatars and building blocks in each of the second spatial building block avatars based on a predetermined building sequence.

21 . The device of claim 19 , wherein the method further comprises: after determining the grid graphs of the second object,
determining, based on a position relationship between the second object and the corresponding first object, a to-be-constructed second spatial building block avatar corresponding to the grid graph, and a position relationship with the corresponding first spatial building block avatar; constructing and rendering the second spatial building block avatar comprises: determining a current to-be-built building block based on a predetermined building sequence and a position relationship between the to-be-constructed second spatial building block avatar and the corresponding first spatial building block avatar; in response to the current to-be-built building block belonging to the second spatial building block avatar, constructing and rendering the building block.

22 . The device of claim 20 , wherein the method further comprises: in a process of the dynam

Assignees

• Lemon Inc

Inventors

• Zeng Weihong
• Wang Xu
• Sun Jingna
• Liu Jing
• Sang Shen
• Lai Chunpong
• Chen Peibin

Classifications

• G06T19/00

  Manipulating three-dimensional [3D] models or images for computer graphics · CPC title

• G06T2210/16

  Cloth · CPC title

• G06T2219/2012

  Colour editing, changing, or manipulating; Use of colour codes · CPC title

• G06T2219/2016

  Rotation, translation, scaling · CPC title

• G06T2219/2008

  Assembling, disassembling · CPC title