Parameter configuration method, apparatus, and device for three-dimensional face model, and storage medium

Patent metadata

Field	Value
Publication number	US-11373384-B2
Application number	US-202117187219-A
Country	US
Kind code	B2
Filing date	Feb 26, 2021
Priority date	Nov 30, 2018
Publication date	Jun 28, 2022
Grant date	Jun 28, 2022

Abstract

This application provides a method for configuring parameters of a three-dimensional face model. The method includes: obtaining a reference face image; identifying a key facial point on the reference face image to obtain key point coordinates as reference coordinates; and determining a recommended parameter set in a face parameter value space according to the reference coordinates. The first projected coordinates are projected coordinates of the key facial point obtained by projecting a three-dimensional face model corresponding to the recommended parameter set onto a coordinate system. The proximity of the first projected coordinates to the reference coordinates meets a preset condition.

First claim

What is claimed is:

1. A method for configuring parameters of a three-dimensional face model, applied to a server in communication with a user terminal, the method comprising:
obtaining a reference face image from the user terminal;
identifying a key facial point on the reference face image to obtain reference coordinates;
determining a recommended parameter set according to the reference coordinates, the recommended parameter set being used for configuring parameters of a three-dimensional face model;
projecting the three-dimensional face model corresponding to the recommended parameter set onto a coordinate system in which the reference coordinates are located, to obtain projected coordinates; and
sending the recommended parameter set to the user terminal, in response to determining a distance between the projected coordinates and the reference coordinates meets a preset condition.

2. The method according to claim 1 , wherein determining the recommended parameter set comprises:
grouping face parameters to obtain a plurality of parameter groups;
determining, for each of the plurality of parameter groups, a plurality of value combinations, and determining, in the plurality of value combinations, a value combination corresponding to projected coordinates closest to the reference coordinates, as a recommended value combination;
combining a plurality of recommended value combinations corresponding to the plurality of parameter groups to form a recommended value combination of face parameters;
and
determining the recommended parameter set according to the recommended value combination of face parameters.

3. The method according to claim 2 , wherein grouping the face parameters comprises:
grouping the face parameters according to degrees to which the face parameters affect the three-dimensional face model and correlation between the face parameters, to obtain the plurality of parameter groups.

4. The method according to claim 3 , wherein grouping the face parameters comprises:
dividing the face parameter into the plurality of parameter groups according to correlation between the face parameters and a specified face region, the specified face region including at least one of a cheek, eyes, eyebrows, a mouth, and a nose.

5. The method according to claim 1 , wherein determining the recommended parameter set of the face parameters comprises:
obtaining a plurality of value combinations formed by grouping the face parameters;
determining, for each of the plurality of value combinations, a distance between projected coordinates corresponding to the each of the plurality of value combinations and the reference coordinates; and
determining the recommended parameter set according to the distance between projected coordinates corresponding to the each of the plurality of value combinations and the reference coordinates.

6. The method according to claim 1 , wherein the distance between the projected coordinates and the reference coordinates is determined by:
determining a conversion parameter according to key facial point coordinates of a reference three-dimensional face model and the reference coordinates;
projecting the three-dimensional face model onto the coordinate system according to the conversion parameter to obtain the second projected coordinates; and
determining a modulus value of a vector difference between the second projected coordinates and the reference coordinates as the distance between the second projected coordinates and the reference coordinates.

7. The method according to claim 1 , wherein determining the recommended parameter set comprises:
determining whether the distance is less than a preset proximity threshold, and determining the recommended value combination of the face parameters as the recommended parameter set in response to that the distance is less than the preset proximity threshold; or
determining whether the distance is in a convergence state, and determining the recommended value combination of the face parameters as the recommended parameter set in response to that the distance is in the convergence state.

8. The method according to claim 7 , further comprising:
updating the reference three-dimensional face model according to the recommended value combination of the face parameters in response to that the distance is neither less than the preset proximity threshold nor in the convergence state.

9. The method according claim 1 , further comprising:
generating a virtual face model according to the recommended parameter set.

10. A method for configuring parameters of a three-dimensional face model, applied to a terminal, the method comprising:
transmitting a request to obtain parameter to a server, the request to obtain parameter carrying a reference face image;
receiving a recommended parameter set returned, according to the request to obtain parameter, by the server, the recommended parameter set being used for configuring parameters of a three-dimensional face model, the recommended coordinates being projected coordinates obtained by projecting the three-dimensional face model onto a coordinate system in which reference coordinates are located; and
receiving the recommended parameter set of the face parameters from the server, in response to determining by the server that a distance between the projected coordinates and the reference coordinates meets a preset condition.

11. The method according to claim 10 , further comprising:
displaying the recommended parameter set on a virtual character configuration interface, the virtual character configuration interface further displaying an adjustment control corresponding to the face parameters.

12. An apparatus including a server for configuring parameters of a three-dimensional face model, the server being in communication with a user terminal, the server comprising: a memory storing computer program instructions; and a processor coupled to the memory and configured to execute the computer program instructions and perform:
obtaining a reference face image from the user terminal;
identifying a key facial point on the reference face image to obtain reference coordinates;
determining a recommended parameter set according to the reference coordinates, the recommended parameter set being used for configuring parameters of a three-dimensional face model;
projecting the three-dimensional face model corresponding to the recommended parameter set onto a coordinate system in which the reference coordinates are located, to obtain projected coordinates; and
sending the recommended parameter set to the user terminal, in response to determining a distance between the projected coordinates the reference coordinates meets a preset condition.

13. The apparatus according to claim 12 , wherein determining the recommended parameter set includes:
grouping face parameters to obtain a plurality of parameter groups;
determining, for each of the plurality of parameter groups, a plurality of value combinations, and determining, in the plurality of value combinations, a value combination corresponding to projected coordinates closest to the reference coordinates, as a recommended value combination;
combining a plurality of recommended value combinations corresponding to the plurality of parameter groups to form a recommended value combination of face parameters;
and
determining the recommended parameter set according to the recommended value combination of the face parameters.

14. The apparatus according to claim 13 , wherein grouping the face parameters includes:
grouping the face parameters according to degrees to which the face parameters af

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Hu Mu
• Gao Sirui
• Ling Yonggen
• Wang Yitong
• Bao Linchao
• Liu Wei

Classifications

• G06V40/168

  Feature extraction; Face representation · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title