Method and apparatus for generating three-dimensional virtual image, and storage medium

1. A method for generating a three-dimensional virtual image, comprising:

obtaining a face image to be processed and a three-dimensional reference model;

obtaining a three-dimensional face model, face attribute information and face image information by inputting the face image to be processed into a trained neural network;

obtaining a three-dimensional image model by performing a deformation process on the three-dimensional reference model based on the three-dimensional face model; and

obtaining a target virtual image by adjusting the three-dimensional image model based on the face attribute information and the face image information,

wherein the method further comprises:

obtaining a plurality of target actions of the target visual image;

obtaining a plurality of deformation coefficients corresponding to the plurality of target actions; and

generating the target visual image by performing a linear superposition on the plurality of deformation coefficients.

2. The method according to claim 1 , wherein obtaining the three-dimensional face model by inputting the face image to be processed into the trained neural network comprises:

extracting a feature vector of the face image to be processed through the trained neural network; and

obtaining the three-dimensional face model based on the feature vector and a preset vector matrix.

3. The method according to claim 2 , further comprising:

obtaining a perspective projection relation corresponding to the three-dimensional face model; and

obtaining texture information of the three-dimensional face model based on the perspective projection relation and the face image to be processed.

4. The method according to claim 1 , wherein obtaining the face image information by inputting the face image to be processed into the trained neural network comprises:

extracting a type of hair style and decorative items in the face image to be processed through the trained neural network.

5. The method according to claim 1 , wherein obtaining the three-dimensional image model by performing the deformation process on the three-dimensional reference model based on the three-dimensional face model comprises:

determining a first deformation area of the three-dimensional face model and a second deformation area of the three-dimensional reference model, wherein the first deformation area and the second deformation area are in a mapping relation;

calibrating a first key point of the first deformation area and a second key point of the second deformation area; and

controlling the first key point to be deformed to cause the second key point to be deformed correspondingly based on the mapping relation, so as to generate the three-dimensional image model.

6. An apparatus for generating a three-dimensional virtual image, comprising:

one or more processors;

a memory storing instructions executable by the one or more processors;

wherein the one or more processors are configured to:

obtain a face image to be processed and a three-dimensional reference model;

obtain a three-dimensional face model, face attribute information and face image information by inputting the face image to be processed into a trained neural network;

obtain a three-dimensional image model by performing a deformation process on the three-dimensional reference model based on the three-dimensional face model; and

obtain a target virtual image by adjusting the three-dimensional image model based on the face attribute information and the face image information,

wherein the one or more processors are further configured to:

obtain a plurality of target actions of the target visual image;

obtain a plurality of deformation coefficients corresponding to the plurality of target actions; and

generate the target visual image by performing a linear superposition on the plurality of deformation coefficients.

7. The apparatus according to claim 6 , wherein the one or more processors are further configured to:

extract a feature vector of the face image to be processed through the trained neural network; and

obtain the three-dimensional face model based on the feature vector and a preset vector matrix.

8. The apparatus according to claim 7 , wherein the one or more processors are further configured to:

obtain a perspective projection relation corresponding to the three-dimensional face model; and

obtain texture information of the three-dimensional face model based on the perspective projection relation and the face image to be processed.

9. The apparatus according to claim 6 , wherein the one or more processors are further configured to: extract a type of hair style and decorative items in the face image to be processed through the trained neural network.

10. The apparatus according to claim 6 , wherein the one or more processors are further configured to:

determine a first deformation area of the three-dimensional face model and a second deformation area of the three-dimensional reference model, wherein the first deformation area and the second deformation area are in a mapping relation;

calibrate a first key point of the first deformation area and a second key point of the second deformation area; and

control the first key point to be deformed to cause the second key point to be deformed correspondingly based on the mapping relation, so as to generate the three-dimensional image model.

11. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to make the computer execute a method for generating a three-dimensional virtual image, and the method comprises:

obtaining a face image to be processed and a three-dimensional reference model;

obtaining a three-dimensional face model, face attribute information and face image information by inputting the face image to be processed into a trained neural network;

obtaining a three-dimensional image model by performing a deformation process on the three-dimensional reference model based on the three-dimensional face model; and

obtaining a target virtual image by adjusting the three-dimensional image model based on the face attribute information and the face image information,

wherein the method further comprises:

obtaining a plurality of target actions of the target visual image,

obtaining a plurality of deformation coefficients corresponding to the plurality of target actions; and

generating the target visual image by performing a linear superposition on the plurality of deformation coefficients.

12. The storage medium according to claim 11 , wherein obtaining the three-dimensional face model by inputting the face image to be processed into the trained neural network comprises:

extracting a feature vector of the face image to be processed through the trained neural network; and

obtaining the three-dimensional face model based on the feature vector and a preset vector matrix.

13. The storage medium according to claim 12 , wherein the method further comprises:

obtaining a perspective projection relation corresponding to the three-dimensional face model; and

obtaining texture information of the three-dimensional face model based on the perspective projection relation and the face image to be processed.

14. The storage medium according to claim 11 , wherein obtaining the face image information by inputting the face image to be processed into the trained neural network comprises:

extracting a type of hair style and decorative items in the face image to be processed through the trained neural network.

15. The storage medium according to claim 11 , wherein obtaining the three-dimensional image model by performing the deformation process on the three-dimensional reference model based on the three-dimensional face model comprises:

determining a first deformation area of the three-dimensional face model and a second deformation area of the three-dimensional reference model, wherein the first deformation area and the second deformation area are in a mapping relation;

calibrating a first key point of the first deformation area and a second key point of the second deformation area; and

controlling the first key point to be deformed to cause the second key point to be deformed correspondingly based on the mapping relation, so as to generate the three-dimensional image model.