Method for repairing and reproducing old films based on deep learning

A deep learning, old technique used in deep learning and computer vision

Active Publication Date: 2018-12-07
福建帝视科技集团有限公司
View PDF11 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If you want to finely repair frame by frame, it will take at least a few months for a movie, and the cost is also in the millions

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 repairing and reproducing old films based on deep learning
  • Method for repairing and reproducing old films based on deep learning
  • Method for repairing and reproducing old films based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] Such as Figure 1-3 As shown in one of the above, the present invention proposes a method for repairing and reproducing old movies based on deep learning. The repair process mainly includes de-interlacing, video de-noising, video de-blurring, video interpolation and super-resolution technology. The specific process is as figure 1 shown. All convolution layers in the present invention use a convolution kernel with a size of 3×3, and the specific steps are as follows:

[0082] Step 1: Extract frames from the video through ffmpeg, and form the training data set of the deinterlacing model, the training data set of the video frame interpolation model, the training data set of the deblurring network and the training data set of the super-resolution model;

[0083] Step 1.1: Form a training data set for the deinterlacing model (model1):

[0084] Step 1.1.1: Extract frames from the video through ffmpeg to obtain each frame of image, scan the obtained video frames in even fie...

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 repairing and reproducing old films based on deep learning, which includes the following steps: S1, extracting the frames of a video through ffmpeg, and forming training data sets of a de-interlacing scanning model, a video frame interpolation model, a de-blurring network and a super-resolution model respectively; S2, training a de-interlacing scanning networkmodel; S3, training a video frame interpolation network model; S4, training a de-blurring network; S5, training a super-resolution network; and S6, training a de-noising network. In the invention, oldfilms are repaired by using de-interlacing scanning, video de-noising, video de-blurring, video frame interpolation and super-resolution technologies based on deep learning. Compared with manual operation, the stability is higher, the computing speed is improved, and the accuracy of image restoration is improved. The method has the advantages of good restoring effect of processed images, high clarity of restored images, convenience of use, low cost, and the like.

Description

technical field [0001] The present invention relates to deep learning and computer vision, in particular to a method for repairing and reproducing old films based on deep learning. Background technique [0002] Film cultural heritage is a precious memory of a country and a nation, an important part of the future intangible cultural heritage, and an excellent carrier for modern Chinese culture to go global. For traditional red movies and movies that reflect the positive spirit of hard work in modern China, modern technology can be used to restore and present them more fully. However, due to the limitations of shooting technology in the past, a large number of old films can no longer meet people's viewing needs for high-definition vision. [0003] There are a huge number of film reels in my country that need to be restored. There are 20,000 to 30,000 feature films in existence, but now only about 60 old film reels can be repaired each year. According to the current restorati...

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): G06T5/00G06T3/40
CPCG06T3/4053G06T5/002G06T5/003G06T2207/10016
Inventor 赵岩聂可卉
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