Variable-length input super-resolution video reconstruction method based on deep learning
A technology of super-resolution and deep learning, which is applied in the field of variable-length input super-resolution video reconstruction based on deep learning, and can solve problems such as inaccurate alignment of long input image sequences
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0073] In order to describe in detail the technical content, operation flow, achieved purpose and effect of the present invention, the following embodiments are given.
[0074] A variable-length input super-resolution video reconstruction method based on deep learning includes the following steps:
[0075] Step 1. Construct training samples of random length and obtain training set;
[0076] Exemplarily, the process of obtaining training samples of random length:
[0077] First, given the input sequence length K, K>0; select the data set;
[0078] Secondly, given the target frame to be reconstructed;
[0079] Finally, select the x frame image on the left side of the target frame and the K-1-x frame image on the right side of the target frame, and arrange the K frame images in order from left to right to obtain the input image sequence;
[0080] Among them, x is an integer randomly obtained by uniform distribution, and x=0, 1,..., K-1.
[0081] The length of the input sequence in the present...
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