Supercharge Your Innovation With Domain-Expert AI Agents!

Multi-frame video compression noise removing method based on deep learning

A deep learning and decompression technology, applied in the field of image processing, can solve problems such as incorrect motion compensation, motion estimation distortion, and inability to obtain denoising results, and achieve the effect of improving denoising performance

Active Publication Date: 2019-12-24
HANGZHOU ARCVIDEO TECHNOLOGY CO LTD
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the input of the model is a multi-frame image with noise, the motion estimation learned by the network is distorted, resulting in incorrect motion compensation, and it is impossible to obtain a good denoising result.

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
  • Multi-frame video compression noise removing method based on deep learning
  • Multi-frame video compression noise removing method based on deep learning
  • Multi-frame video compression noise removing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0032] Such as figure 1 In the described embodiment, a kind of deep learning-based multi-frame video decompression noise method specifically includes the following steps:

[0033] (1) Prepare data: construct a data set, obtain noise images, and take three consecutive frames of noise images as a group, and sample image blocks for each group of images, and the input of the model is composed of these image blocks.

[0034] The specific operation steps are as follows:

[0035] (11) The data set consists of clear short videos with different contents. Each video has several frames of images. Since the data required by the model is continuous multi-frame images, each frame of image is saved in PNG format as a label for noise images. , and the noise image is to compress the clear video according to different compression methods, and then save each fr...

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 multi-frame video compression noise removing method based on deep learning. Based on a deep learning technology, the invention provides a multi-frame video compression noiseremoving model, the input of the model is the continuous multi-frame noise images, and through the pre-noise removing, motion compensation and image enhancement modules, the residual noise of an intermediate frame is learned to obtain a better noise removed image. The beneficial effects of the invention are that the noise removing performance is improved through a motion compensation technology and by employing the information contained in the adjacent frames; through the pre-noise removing operation, some serious noises are effectively removed in advance, and the subsequent noise removing performance is improved.

Description

technical field [0001] The present invention relates to the technical field related to image processing, in particular to a method for decompressing noise in multi-frame video based on deep learning. Background technique [0002] In real life, the process of image digitization and transmission is often affected by imaging equipment and external environmental noise interference, which leads to a decrease in the quality of the acquired image. However, in many image application fields, the requirements for image quality are very high. For example, the image quality of video decreases after compression, and factors such as compression method, compressed bit rate, and video content will cause different noises in the image, hindering people's understanding of the video content. Most of the current denoising algorithms are aimed at single-frame images, such methods ignore the information contained in adjacent frames, so their performance is largely limited. [0003] In recent yea...

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): G06T5/00G06N3/04
CPCG06T2207/10016G06T2207/20084G06T2207/20081G06N3/045G06T5/70
Inventor 徐烂烂陈梅丽谢亚光
Owner HANGZHOU ARCVIDEO TECHNOLOGY CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com