Image stylization processing method, apparatus, device, storage medium, and computer program

Abstract

This disclosure relates to an image stylization processing method, apparatus, device, storage medium, and program product, the method comprising: acquiring a source image input by a user; displaying at least one conditional constraint information; generating a target conditional feature based on the conditional constraint information corresponding to an operation on the at least one conditional constraint information; and generating a target image based on the target conditional feature.

Claims

1. A method for processing image styles, Obtaining the original image entered by the user, Display at least one conditional constraint, In response to an operation on at least one of the aforementioned conditional constraints, a target conditional feature is generated based on the conditional constraint information corresponding to the operation. An image stylization method, comprising generating a target image based on the aforementioned target condition features.

2. In response to an operation on at least one of the aforementioned conditional constraints, generating a target conditional feature based on the conditional constraint information corresponding to the operation is: In response to a selection operation on the aforementioned constraint information, at least one of the plurality of constraint information is selected as the target constraint information. For each of the aforementioned target condition constraints, in response to a setting operation on the control information corresponding to the aforementioned target condition constraints, the target control information corresponding to the aforementioned target condition constraints is acquired. The method according to claim 1, comprising generating target condition features based on at least one target condition constraint information and target control information corresponding to the target condition constraint information.

3. Generating target condition features based on at least one of the aforementioned target condition constraints and target control information corresponding to the aforementioned target condition constraints is: For each of the aforementioned target conditional constraints, the aforementioned target conditional constraints are input into the corresponding conditional model to perform feature extraction and obtain initial conditional features. The method according to claim 2, comprising generating target condition features based on the initial condition features and the target control information.

4. The target control information includes the target condition weights, Generating target condition features based on the initial condition features and the target control information is: The method according to claim 3, comprising performing a weighting calculation based on at least one of the initial condition features and a target condition weight corresponding to the initial condition feature to obtain a target condition feature.

5. The target control information includes the target condition mask, Generating target condition features based on the initial condition features and the target control information is: The method according to claim 3, comprising applying the target condition mask to at least one of the initial condition features to generate a target condition feature.

6. In response to a setting operation on the control information of the aforementioned target condition constraint information, acquiring target control information corresponding to the aforementioned target condition constraint information is: Display multiple selection waiting condition masks, and in response to a selection operation on the selection waiting condition masks, set the selected selection waiting condition mask as the target condition mask corresponding to the target condition constraint information, and / or The method according to claim 5, comprising, in response to detection that a slide operation has constituted a sealed area, masking the sealed area and then forming a target condition mask corresponding to target condition constraint information.

7. The aforementioned conditional constraint information includes conditional information obtained after feature extraction has been performed on the conditional image, The method according to claim 1, wherein the conditional image includes a source image and / or a reference image corresponding to the source image, and the feature extraction method includes at least one of edge extraction, keypoint detection, and pose detection.

8. Generating a target image based on the aforementioned target condition features is: The original image is input into the target stylization model, The aforementioned target condition features are input into the target stylization model as constraints, The method according to claim 1, further comprising generating a target image using the target stylization model.

9. An image stylization processing device, A source image acquisition module for obtaining the source image entered by the user, A constraint information display module for displaying at least one constraint information, A target condition feature generation module for generating target condition features based on condition constraint information corresponding to an operation on at least one of the condition constraint information, An image stylization processing apparatus comprising a target image generation module for generating a target image based on the aforementioned target condition features.

10. It is an electronic device, One or more processors, Includes a memory device for storing one or more programs, An electronic device that, when one or more of the aforementioned programs are executed by one or more of the aforementioned processors, causes one or more of the aforementioned processors to implement the image stylization processing method according to any one of claims 1 to 8.

11. A computer-readable storage medium that stores a computer program and, when the program is executed by a processor, enables the image stylization processing method described in any one of claims 1 to 8.

Images