Generating image method and apparatus, device, and medium
View Patent ↗The embodiments of the present disclosure relate to an image generation method, apparatus, device, and medium. The method includes: obtaining an initial image of a target object, where the initial image is an image in a first image style; inputting the initial image into a first machine learning model; and obtaining a target image of the target object based on an output result of the first machine learning model, where the target image is an image in a second image style. The first machine learning model is obtained based on a second machine learning model obtained based on training first sample images of the target object and second sample images of the target object. The first sample image and the second sample image are respectively images obtained by rendering simulation models of the target object in different states based on rendering parameters in the first and second image styles.
1 . A method for generating an image, comprising:
obtaining an initial image of a target object, wherein the initial image is an image in a first image style; and
inputting the initial image into a first machine learning model, and obtaining a target image of the target object based on an output result of the first machine learning model, wherein the target image is an image in a second image style; wherein
the first machine learning model is obtained based on a second machine learning model, the second machine learning model is obtained based on training first sample images of the target object and second sample images of the target object, the first sample images are images obtained by rendering simulation models of the target object in different states based on rendering parameters in the first image style, and the second sample images are images obtained by rendering simulation models of the target object in different states based on rendering parameters in the second image style; and
the simulation models are configured to construct images of the target object in different states, and the different states comprise at least one of: different shapes of the target object, or different postures of the target object.
2 . The method according to claim 1 , wherein the first machine learning model is the second machine learning model.
3 . The method according to claim 1 , wherein the first machine learning model is obtained by training third sample images of the target object and fourth sample images of the target object, the third sample images are images in the first image style, and the fourth sample images are images output by the second machine learning model by inputting the third sample images into the second machine learning model.
4 . The method according to claim 1 , wherein the simulation models of the target object in different states are obtained by adjusting a state parameter of an initial simulation model of the target object.
5 . The method according to claim 1 , wherein the rendering parameters comprises at least one of a texture parameter, a color parameter, an illumination parameter and a special effect parameter of the target object, and
at least one parameter of the rendering parameters in the first image style and the second image style are different.
6 . The method according to claim 5 , wherein the rendering parameters further comprises a background parameter, and the background parameter and the illumination parameter are randomly adjusted in a rendering process.
7 . The method according to claim 1 , wherein the target object comprises a hand or a foot.
8 . An electronic device, comprising a memory and a processor, wherein the memory stores a computer program which, when executed by the processor, causes the electronic device to:
obtain an initial image of a target object, wherein the initial image is an image in a first image style; and
input the initial image into a first machine learning model, and obtain a target image of the target object based on an output result of the first machine learning model, wherein the target image is an image in a second image style; wherein
the first machine learning model is obtained based on a second machine learning model, the second machine learning model is obtained based on training first sample images of the target object and second sample images of the target object, the first sample images are images obtained by rendering simulation models of the target object in different states based on rendering parameters in the first image style, and the second sample images are images obtained by rendering simulation models of the target object in different states based on rendering parameters in the second image style; and
the simulation models are configured to construct images of the target object in different states, and the different states comprise at least one of: different shapes of the target object, or different postures of the target object.
9 . The electronic device according to claim 8 , wherein the first machine learning model is the second machine learning model.
10 . The electronic device according to claim 8 , wherein the first machine learning model is obtained by training third sample images of the target object and fourth sample images of the target object, the third sample images are images in the first image style, and the fourth sample images are images output by the second machine learning model by inputting the third sample images into the second machine learning model.
11 . The electronic device according to claim 8 , wherein the simulation models of the target object in different states are obtained by adjusting a state parameter of an initial simulation model of the target object.
12 . The electronic device according to claim 8 , wherein the rendering parameters comprises at least one of a texture parameter, a color parameter, an illumination parameter and a special effect parameter of the target object, and
at least one parameter of the rendering parameters in the first image style and the second image style are different.
13 . The electronic device according to claim 12 , wherein the rendering parameters further comprises a background parameter, and the background parameter and the illumination parameter are randomly adjusted in a rendering process.
14 . The electronic device according to claim 8 , wherein the target object comprises a hand or a foot.
15 . A non-transitory computer-readable storage medium storing a computer program which, when executed by a computing device, causes the computing device to perform:
obtaining an initial image of a target object, wherein the initial image is an image in a first image style; and
inputting the initial image into a first machine learning model, and obtaining a target image of the target object based on an output result of the first machine learning model, wherein the target image is an image in a second image style; wherein
the first machine learning model is obtained based on a second machine learning model, the second machine learning model is obtained based on training first sample images of the target object and second sample images of the target object, the first sample images are images obtained by rendering simulation models of the target object in different states based on rendering parameters in the first image style, and the second sample images are images obtained by rendering simulation models of the target object in different states based on rendering parameters in the second image style; and
the simulation models are configured to construct images of the target object in different states, and the different states comprise at least one of: different shapes of the target object, or different postures of the target object.
16 . The non-transitory computer-readable storage medium according to claim 15 , wherein the first machine learning model is the second machine learning model.
17 . The non-transitory computer-readable storage medium according to claim 15 , wherein the first machine learning model is obtained by training third sample images of the target object and fourth sample images of the target object, the third sample images are images in the first image style, and the fourth sample images are images output by the second machine learning model by inputting the third sample images into the second machine learning model.
18 . The non-transitory computer-readable storage medium according to claim 15 , wherein the simulation models of the target object in different states are obtained by adjusting a state parameter of an initial simulation model of the target object.
19 . The non-transitory computer-readable storage medium according to claim 15 , wherein the rendering parameters comprises at least one of a texture parameter, a color parameter, an illumination parameter and a special effect parameter of the target object, and at least one parameter of the rendering parameters in the first image style and the second image style are different.
20 . The non-transitory computer-readable storage medium according to claim 19 , wherein the rendering parameters further comprises a background parameter, and the background parameter and the illumination parameter are randomly adjusted in a rendering process.