Unlock instant, AI-driven research and patent intelligence for your innovation.

A multi-branch video super-resolution method and system based on dynamic reconstruction

A super-resolution and multi-branch technology, applied in the field of image processing, can solve the problem of high computing cost of super-resolution, and achieve the effects of low computing cost, improved reconstruction ability, and improved performance

Active Publication Date: 2021-03-30
四川省人工智能研究院(宜宾)
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a multi-branch video super-resolution method and system based on dynamic reconstruction, which solves the problem of high computational cost of existing video super-resolution

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A multi-branch video super-resolution method and system based on dynamic reconstruction
  • A multi-branch video super-resolution method and system based on dynamic reconstruction
  • A multi-branch video super-resolution method and system based on dynamic reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0047] Such as figure 1 As shown, the multi-branch video super-resolution method based on dynamic reconstruction includes the following steps:

[0048] S1. Taking the frame sequence extracted from the target video as an input data in units of 7 frames;

[0049] S2. Input all 7 frames of the input data into the first branch, input the middle 5 frames of the input data into the second branch, input the middle 3 frames of the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-branch video super-resolution method and system based on dynamic reconstruction. The method includes the following steps: S1, taking 7 frames as an input data; S2, respectively passing through the first branch, the second branch and the The third branch obtains a feature map; S3, adjusts the size of the three feature maps to obtain the adjusted data; S4, performs dimension adjustment to obtain the dimension-adjusted data; S5, obtains weights according to the dimension-adjusted data; S6, Multiply the feature map generated by each branch by the corresponding weight, and use the sum of the three multiplication results as the target feature map; S7, perform sub-pixel convolution upsampling on the target feature map to complete video super-resolution. The present invention adopts a multi-branch network structure, and the information transfer between branches makes full use of the information dependency between feature maps of different sizes, so that the performance of the neural network is greatly improved, and the calculation cost is small.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a multi-branch video super-resolution method and system based on dynamic reconstruction. Background technique [0002] Super-resolution refers to the process of converting low-resolution images to high-resolution. In the past few years, the super-resolution problem has attracted more and more attention in the field of computer vision, and there are many models that have achieved great success in the direction of single-image super-resolution. Very good effects, such as DBPN (Deep Back-Projection Networks), this method uses an error feedback mechanism that iteratively calculates the upsampling and downsampling projection errors, and guides the reconstruction process to get better results. RDN (Residual Dense Networks), stacking multiple residual dense blocks, proposes a residual dense network, making full use of the characteristics of each level in the network. RCAN (R...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/40G06N3/04H04N21/4402
CPCG06T3/4053H04N21/440263G06T3/4076G06N3/045
Inventor 邵杰张东阳梁振文申恒涛
Owner 四川省人工智能研究院(宜宾)
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com