All-focus image generation method based on interactive adversarial learning
An all-focus image and non-focus technology, applied in the field of all-focus image generation, can solve problems such as difficult to extract deep features, low model complexity, and poor robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0035] The specific implementation manners of the present invention will be further described below in conjunction with the accompanying drawings and technical solutions.
[0036] Figure 1The flow chart of the overall training method of the omni-focus image generation network, first builds the non-focus blur detection network, obtains the intermediate output, that is, the non-focus blur detection map, and then inputs it into the omni-focus image generation network together with the input image to obtain the full Focus on the image, use formula (1-6) as the loss function for supervision, and when the generator and the discriminator reach the final dynamic equilibrium point, the training of this model ends. After this process, we can get an omni-focus image generator with good performance.
[0037] In general, this method designs an omni-focus image generation method based on interactive adversarial learning, which can effectively complete the global consistent and natural omn...
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