Portrait-based video generation method and device, and storage medium
A portrait and video technology, which is applied in the field of portrait-based video generation methods and devices, and storage media, and can solve problems such as lack of universality.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0043] As mentioned earlier, the current method of generating portrait-based videos based on modeling based on a specific portrait is not universal enough.
[0044] In view of the above problems, the embodiment of the present invention uses the trained Generative Adversarial Networks (GANs) to perform corresponding feature extraction processing and feature fusion on the input target face static image and portrait expression control data, and generate an image sequence , and output the generated image sequence when it is determined that the generated image sequence reaches a preset authenticity threshold. Using the video generation method of the embodiment of the present invention, it is not necessary to carry out special modeling for a specific portrait, so when the target portrait is replaced, it is not necessary to readjust the trained generation confrontation network model, so it has stronger universality It can also reduce the cost of video generation because it does not n...
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