Hyperspectral image super-resolution reconstruction method based on depth image prior
A technology for super-resolution reconstruction and hyperspectral image, which is applied in image analysis, image enhancement, image and image conversion, etc. It can solve the problems of unsatisfactory results and small number of hyperspectral image data sets, so as to improve the quality , Extend the effect of the application
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0084] As an optional implementation manner of the present invention, the step 6 includes:
[0085] Step 61: input white noise having the same size as the supramolecular image block to be input into the super-resolution reconstruction network to obtain an output image;
[0086] Step 62: Calculate the loss function between the output image and the supramolecular image block to be down-sampled;
[0087] Step 63: Adjusting the parameters of the super-resolution reconstruction network through backpropagation to train the super-resolution reconstruction network up to the optimal number of iterations to obtain reconstructed sub-blocks;
[0088] Step 64: Integrate the reconstructed sub-blocks to obtain a reconstructed hyperspectral image.
[0089] It is worth noting that the present invention needs to integrate super-resolved sub-images to form an image. Each super-resolved sub-block is integrated into the final super-resolved hyperspectral image.
[0090] It is worth noting that:...
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