A video super-resolution reconstruction method based on depth learning

A technology of super-resolution reconstruction and deep learning, applied in neural learning methods, image data processing, instruments, etc.

Active Publication Date: 2018-12-28
CHINA JILIANG UNIV
View PDF2 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) SR is an inverse problem, and i

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 video super-resolution reconstruction method based on depth learning
  • A video super-resolution reconstruction method based on depth learning
  • A video super-resolution reconstruction method based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0023] like image 3 As shown, the video super-resolution reconstruction method based on deep learning of the present invention comprises the following steps:

[0024] Step 1: Training and testing data preparation: (1) Collection of public data sets: Collect two sets of M pairs of public videos with the same content, one set is a low-resolution video, and the other set is a corresponding high-definition video; (2) Private data Set collection: use different mobile phones and different cameras to shoot high-definition videos, and collect N groups of high-definition videos in total, and use H i (i=1, 2, ... N) represent; The high-definition video H that will collect i Use an adversarial network to generate low-resolution videos with various camera motions, multiple scene depths, and multiple motion blurs, where the camera motion V i a (a=...

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 video super-resolution reconstruction method based on depth learning. The technical key points are: (1) continuous images are given under the same shot, the network predictsclearer video frame images; (2) using a bi-directional circulating neural network and a depth 3D back projection network; (3) the invention combines two networks into one network, and the network is used as a network (4) for in-depth learning video super-resolution reconstruction of the invention. The training data is labeled, and the processed data video frames are passed through the network to obtain a loss function. A final object of the present invention is to input temporal and spatial information of a low-resolution video frame predicted by a bi-directional circulating network, after the3D projection network re-predicts the details of the video frame, an optimal model is obtained after repeated training. The model is applied to remove the effects of the camera shake, the blur of theobject's fast motion, out-of-focus blur, lens optical blur, depth-of-field variation, compression distortion and noise, and other degradation factors.

Description

technical field [0001] The invention belongs to the field of video processing, in particular to a video super-resolution reconstruction method based on deep learning. Background technique [0002] Video super-resolution (super resolution, SR) is the process of obtaining high-resolution video from a low-resolution video. This technology is mainly used to enhance the spatial resolution of the video, which can break through the limitations of the original system imaging hardware conditions. Due to limitations, the re-obtained high-resolution video has higher resolution, more detailed information, and higher-quality picture quality. It is currently one of the most effective and cheapest ways to obtain high-resolution video. [0003] In the process of video acquisition, limited by factors such as imaging conditions and imaging methods, the imaging system usually cannot acquire all the information in the original scene, and it will be affected by many factors such as vibration, de...

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
IPC IPC(8): G06T3/40G06N3/04G06N3/08
CPCG06N3/084G06T3/4046G06T3/4053G06N3/045Y02T10/40
Inventor 章东平张香伟倪佩青
Owner CHINA JILIANG UNIV
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
Try Eureka
PatSnap group products

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