Video super-resolution reconstruction method based on deep residual network

A super-resolution reconstruction and high-resolution technology, applied in the field of video super-resolution reconstruction based on deep residual network, can solve the problems of unsatisfactory reconstruction effect, complex video content, and video image brightness distortion, etc. Show the effect of the effect

Inactive Publication Date: 2017-10-20
福建帝视科技集团有限公司
View PDF6 Cites 51 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Although relevant research has achieved good video super-resolution reconstruction effects, sometimes due to the complexity of the video content, the reconstruction effect is not satisfactory, and even the brightness of the video image will be distorted.

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
  • Video super-resolution reconstruction method based on deep residual network
  • Video super-resolution reconstruction method based on deep residual network
  • Video super-resolution reconstruction method based on deep residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] like Figure 1-6 As shown in one of them, the present invention discloses a method for super-resolution reconstruction of network video based on depth residual, which includes the following steps:

[0039] In step 1, the current frame in the high-resolution video sequence will be It is regarded as a key frame, and then the preceding T frame and the following T frame of the key frame are taken. Therefore, a set of high-resolution video images in a video sequence Contains 2T+1 frames, index t∈{-T,-T+1,...,0,...T-1,T};

[0040] Step 2, a set of high-resolution video images obtained through step 1 Generate a set of 2T+1 frame low-resolution video image sequences with one-to-one correspondence with the scaling ratio S current frame The low-res video image for Further, the scaling ratio S in step 2 includes three representative scales of 2 times, 3 times and 4 times;

[0041] Step 3, will use the CLG-TV optical flow model algorithm [5] Compute all low-resolution...

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 a deep residual network. According to the method, a corresponding high-resolution image is reconstructed from a set of continuous low-resolution video frame images of a video sequence so that the video display effect can be obviously enhanced. The innovativeness of the video super-resolution algorithm is mainly reflected in two aspects: firstly, the initial stage, the series convolutional layer computation stage and the residual block computation stage are directly performed from the low-resolution video images by using the deep residual network and then the high-resolution video image is reconstructed by using the deconvolution and convolution operation mode gradually so that conventional preprocessing of bicubic interpolation does not need to be performed on the low-resolution video images; and secondly, compared with the most classic single frame and video super-resolution reconstruction method based on deep learning, the high-resolution video image can be effectively reconstructed in different environments under the condition of using few training data, and the video image display effect can be greatly enhanced.

Description

technical field [0001] The invention belongs to the field of video super-resolution, in particular to a video super-resolution reconstruction method based on a deep residual network. Background technique [0002] Video super-resolution reconstruction is a technique for reconstructing a corresponding high-resolution image from a set of continuous low-resolution video frame images in a video sequence. With the continuous improvement of the resolution of terminal display devices, this technology has broad application prospects in the fields of online video live broadcast, high-definition TV video, and high-definition movie production. [0003] In the actual application environment, due to the performance limitations of network bandwidth and video streaming equipment, even if the terminal equipment can support the display of ultra-high-definition (UHD, Ultra High Definition) or high-definition (HD, High Definition) images / videos, it cannot Receive and display UHD or HD images / v...

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): G06T3/40H04N7/01
CPCG06T3/4053H04N7/0125H04N7/0127H04N7/0135
Inventor 李根童同高钦泉
Owner 福建帝视科技集团有限公司
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