Interactive image editing method, system, readable storage medium and electronic equipment
An image editing and interactive technology, applied in the field of image editing, can solve the problems of global influence, long training time, insufficient image detail processing, etc., achieving fast speed, small user workload, and good effect.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0059] see figure 1 , shows the interactive image editing method in the first embodiment of the present invention, the method specifically includes steps S101 to S105:
[0060] S101. Obtain an edited image, where the edited image includes an original image and a feature image pasted on a target area of the original image;
[0061] During specific implementation, the original image and the feature image are acquired, and the feature image is pasted on the target area of the original image as the edited image.
[0062] It should be noted that the original image is any picture in the FFHQ face dataset, and the user can select it by himself, and the user can also select the target area of the original image (such as eyes, hair), and the feature image can be selected by the user from any Select from a picture.
[0063] S102, inputting the edited image into a generator in the trained generative confrontation network structure;
[0064] In specific implementation, the Genera...
Embodiment 2
[0099] Another aspect of the present invention also proposes an interactive image editing system, please refer to image 3 , shows the interactive image editing system in the second embodiment of the present invention, the system includes:
[0100] An acquisition module 11, configured to obtain an edited image, which includes an original image and a feature image pasted on a target area of the original image;
[0101] The input module 14 is used to input the edited image into the generator in the trained generative confrontation network structure;
[0102] It should be noted that, in this application, the trained generative confrontation network structure selects the StyleGAN2 network structure, and before the input module, the system also includes:
[0103] Division module 12, for dividing the generator in the StyleGAN2 into a first part and a second part;
[0104] An introduction module 13, configured to sequentially introduce adaptive spatial attention and adaptive chan...
Embodiment 3
[0132] The present invention also proposes an electronic device, please refer to Figure 4 , is shown as an electronic device in the third embodiment of the present invention, including a memory 10, a processor 20, and a program 30 stored in the memory 10 and operable on the processor 20, and the processor 20 executes the program 30 implement the above method.
[0133] During specific implementation, the processor 20 obtains an edited image, the edited image includes an original image and a feature image pasted on a target area of the original image;
[0134] The processor 20 inputs the edited image into a generator in the trained generative confrontation network structure;
[0135] The processor 20 utilizes adaptive spatial attention in the generator to optimize the region of the feature image in the edited image to obtain an edited image with spatial attention features;
[0136] The processor 20 uses the adaptive channel attention in the generator to automatically assign...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com