Deep network video denoising method based on model constraint and program product

A deep network and video technology, applied in the field of video denoising, can solve the problem that the denoising effect is not completely exceeded, and the video quality cannot be effectively guaranteed, so as to reduce the computational complexity and improve the video quality.

Pending Publication Date: 2022-08-02
XIDIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the technical problem that the current video denoising method based on deep learning does not completely exceed the traditional model-based method, and t

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
  • Deep network video denoising method based on model constraint and program product
  • Deep network video denoising method based on model constraint and program product
  • Deep network video denoising method based on model constraint and program product

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0070] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.

[0071] The purpose of the present invention is to design a video denoising method based on model guidance, which overcomes the high computational complexity of existing traditional model-based video denoising methods, poor interpretability of deep learning-based video denoising methods, and traditional optical flow alignment methods. The problem of low efficien...

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 belongs to a video denoising method, and provides a deep network video denoising method based on model constraint and a program product in order to solve the technical problems that the denoising effect of an existing video denoising method based on deep learning does not completely exceed that of a traditional method based on a model, and the quality of a denoised video cannot be effectively guaranteed. For video denoising, a new video denoising network based on model guidance is provided as an observation model, the video denoising network describes the relationship between adjacent noise frames, a clean video frame can be effectively recovered through maximum posterior probability estimation, and effective calculation can also be performed through iteration steps. Compared with a traditional observation model, the new observation model provided by the invention has the advantages that the calculation complexity is greatly reduced by realizing effective iteration steps, and the video quality after noise reduction can be effectively improved.

Description

technical field [0001] The invention belongs to a video denoising method, in particular to a deep network video denoising method and program product based on model constraints. Background technique [0002] Despite the ever-improving performance of imaging sensors, digital imaging still inevitably introduces noise, which not only degrades image and video quality, but also adversely affects subsequent image processing tasks. [0003] In order to improve the visual effect, researchers at home and abroad have proposed many image and video denoising algorithms. For single image denoising, existing methods are mainly divided into model-based methods and deep learning-based methods. Model-based denoising methods are highly flexible, but have high computational complexity and are difficult to jointly optimize the parameters in the algorithm. With the rise of deep learning, Convolution Neural Network (CNN) has also been used for image denoising. By learning an end-to-end mapping f...

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): G06T5/00G06T5/50G06N3/04G06N3/08
CPCG06T5/002G06T5/50G06N3/084G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/20221G06N3/045
Inventor 董伟生樊本超王屹晨董乐石光明
Owner XIDIAN 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