Method for improving frame rate up conversion effect by using generated network

A frame rate, conversion algorithm technology, applied in the field of deep neural network, can solve the problem of no expected difference

Inactive Publication Date: 2018-01-19
HANGZHOU DIANZI UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the image pixels obtained by the traditional technology using MSE (mean square error) as the loss function are too smooth, and the local texture details are less. Although the low-quality images on PSNR have been greatly improved, the visual experience There is no expected difference, but an adversari

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
  • Method for improving frame rate up conversion effect by using generated network
  • Method for improving frame rate up conversion effect by using generated network
  • Method for improving frame rate up conversion effect by using generated network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be described in detail below in combination with specific embodiments.

[0047] As shown in Figure 1-3, a method of using the generative network to improve the frame rate up-conversion effect, the specific steps are as follows:

[0048] Step 1: Compress the original video through JM18.6 to obtain the compressed video, then reconstruct the even-numbered frames by retaining the odd-numbered frames, and use the traditional frame rate up-conversion algorithm to obtain the even-numbered frames The reconstructed frame. The reconstruction frame generation method is as follows:

[0049] 1-1. Using the motion estimation method to obtain the optimal forward motion vector v f and the optimal backward motion vector v b . That is, find in the candidate forward motion vector such that formula (1) SAD f The vector with the smallest value is used as the optimal forward motion vector, and similarly find the formula (3) SAD in the candidate backward motion...

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 method for improving frame rate up conversion effect by using a generated network. The method comprises the following steps of 1, comprising an original video via JM18.6 to acquire the compressed video, then reserving odd-number frames in the compressed video, and reconstructing even-number frames to acquire reconstructed frames of the even-number frames by using a framerate up conversion algorithm based on direction selection movement estimation; 2, building a generated network G, inputting the reconstructed frames IE into a neural network for training, comparing the corresponding frames IP in the original video with network output, backwards propagating an error, and acquire the optimal remediation effect after multiple times of adjustment; 3, repeatedly executing the steps 1 and 2 until an error variation rate is invariable or less than a set threshold; and 4, applying the trained network, inputting the reconstructed frames has been subjected to frame rateup conversion into the network to acquire an image with high quality. According to the method provided by the invention, psnr values and quality of the reconstructed frames are improved, and thus theframe rate up conversion effect is improved.

Description

technical field [0001] The invention relates to the fields of deep neural network and frame rate up-conversion, in particular to CNN structure network and residual structure. technical background [0002] Video information is one of the most important information sources for human beings, and occupies a large proportion in the field of signal processing. The essence of the existing video source is the result of spatial and temporal sampling after the active three-dimensional scene is projected onto a two-dimensional plane. Frame rate up-conversion, also known as time interpolation, is an important part of video format conversion technology. It is mainly used to realize the conversion between different frame rate display formats. For example, if a movie film shot at 24 frames per second is played on a high-definition television above 60 frames per second, frame rate up-conversion must be used to convert between the two formats. In low-bit-rate video communication, it is of...

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): H04N19/176H04N19/149H04N19/129H04N19/587H04N19/139
Inventor 陈立鑫颜成钢张永兵朱翱宇
Owner HANGZHOU DIANZI 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