Image super-resolution processing method based on probabilistic generative model
A technology for generating models and processing methods, applied in the field of image processing, which can solve the problems of limiting the resolution of high-resolution images, not taking into account the use of model prior information, and being unable to utilize all information, so as to achieve the effect of improving the resolution.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034] The present invention will be further described below in conjunction with the accompanying drawings.
[0035] refer to figure 1 , The specific implementation steps of the present invention are as follows.
[0036] Step 1. Input image.
[0037] Input multiple high-resolution optical images into the training set.
[0038] Multiple high-resolution optical images different from those in the training set are input into the test set.
[0039] Step 2. Get training samples.
[0040] For each high-resolution optical image in the training set, the bicubic interpolation method is used after down-sampling to obtain a low-resolution image with the same size as the high-resolution image.
[0041] The down-sampling process refers to down-sampling the high-resolution optical image with scaling factors of 2, 3, and 4 to obtain low-resolution images with sizes of 8×8 pixels, 10×10 pixels, and 12×12 pixels.
[0042] Image blocks of the same size are extracted from the same position o...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap