Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Apparatus and method for unsupervised video super-resolution using generative adversarial networks

A super-resolution and low-resolution technology, applied in the field of video super-resolution and VSR of machine learning models

Pending Publication Date: 2021-09-21
THE HONG KONG UNIV OF SCI & TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, previous methods fuse LR frames based on motion compensation and assume that all frames are temporally correlated, which may introduce noise information from previous frames

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
  • Apparatus and method for unsupervised video super-resolution using generative adversarial networks
  • Apparatus and method for unsupervised video super-resolution using generative adversarial networks
  • Apparatus and method for unsupervised video super-resolution using generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In the following description, devices for VSR, training methods, GAN architecture, etc. are set forth as preferred examples. It will be apparent to those skilled in the art that modifications including additions and / or substitutions can be made without departing from the scope and spirit of the present invention. Specific details may be omitted so as not to obscure the invention. However, this disclosure was written to enable those skilled in the art to practice the teachings herein without undue experimentation.

[0026] It should be apparent to those skilled in the art that the foregoing examples of digital drive methods are only intended to illustrate the working principle of the present invention. It is not intended to be exhaustive or to limit the invention to the precise forms disclosed.

[0027] Euclidean distance as used herein is also called Euclidean distance, which is a distance metric that measures the absolute distance between two points in a multidimensi...

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

A method of video super-resolution (VSR) with temporal consistency using a generative adversarial network (VistGAN) that only requires training a high resolution video sequence to generate pairs of high resolution / low resolution video frames for training, without the need for pre-artificially synthesized pairs of high resolution / low resolution video frames for training. By this unsupervised learning approach, the encoder degenerates the input high-resolution video frame training the high-resolution video sequence to its low-resolution counterpart, and the decoder attempts to recover the original high-resolution video frame from the low-resolution video frame. To improve temporal coherency, an unsupervised learning approach provides a sliding window that explores temporal coherency in a high resolution domain and a low resolution domain. It maintains time consistency and also makes full use of high frequency details from the reconstructed high resolution video frame generated last time.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 100,272, filed March 5, 2020, the disclosure of which is incorporated herein by reference in its entirety. technical field [0003] The present invention generally relates to techniques for reconstructing high-resolution (HR) video from their low-resolution (LR) counterparts, known as video super-resolution (VSR). More specifically, the present invention relates to VSR using machine learning models. Background technique [0004] VSR is the reconstruction of HR video sequences from their LR counterparts and has recently attracted a lot of attention due to the development of high-definition (HD) displays and the wide application of VSR in video surveillance, storage, and streaming. The VSR is designed to base on the input LR video sequence Estimating HR Video Sequences This HR video sequence should be close to the actual counterpart HR vi...

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 Applications(China)
IPC IPC(8): G06T3/40G06T7/269G06N3/08
CPCG06T3/4053G06T3/4046G06T7/269G06N3/088G06T2207/10016G06T2207/20081G06T2207/20084H04N19/59G06N3/047G06N3/045G06N20/00
Inventor 陈双幸闻嵩
Owner THE HONG KONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

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