Super-resolution reconstruction method, device and equipment apparatus and storage medium

A technology of super-resolution reconstruction and resolution reconstruction, which is applied in the field of image processing and can solve problems such as inability to obtain super-resolution effects and poor generalization effects of super-resolution reconstruction methods

Active Publication Date: 2020-06-26
TENCENT TECH (SHENZHEN) CO LTD
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] A super-resolution reconstruction method based on deep learning has been proposed in related technologies, but the generalization effect of the super-resolution reconstruction method in

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
  • Super-resolution reconstruction method, device and equipment apparatus and storage medium
  • Super-resolution reconstruction method, device and equipment apparatus and storage medium
  • Super-resolution reconstruction method, device and equipment apparatus and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0036] The embodiments of the present application will be described below in conjunction with the drawings.

[0037] When performing super-resolution reconstruction in related technologies, simple end-to-end mapping processing methods are often used, that is, low-resolution images are processed directly to obtain super-resolution reconstruction results through model processing. However, this method is generalized in the face of real online scenes. The effect is poor, and in some scenes, a satisfactory over-scoring effect is often not obtained.

[0038] To this end, the embodiments of the present application provide a super-resolution reconstruction method based on artificial intelligence. After the initial reconstructed video frame is obtained based on the resolution reconstruction model, the initial reconstructed video frame can be post-processed so that the initial reconstructed video frame The high-frequency details are clearer to obtain the best result of the picture quality in...

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 embodiment of the invention discloses a super-resolution reconstruction method, device and equipment apparatus based on artificial intelligence, and a storage medium, and the method comprises thesteps: obtaining a to-be-processed video frame sequence of a first resolution when the super-resolution reconstruction of a certain video file is needed, and enabling wherein the to-be-processed videoframe sequence to be is the video frame sequence of the video file; for each to-be-processed video frame in the to-be-processed video frame sequence, performing resolution reconstruction on the eachto-be-processed video frame according to the resolution reconstruction model to obtain an initial reconstructed video frame with a second resolution, wherein ; second resolution is higher than first resolution. D; determining a contour region in the initial reconstructed video frame through a residual separation mode; and carrying out contour enhancement processing is performed on the contour region to obtain a target reconstructed video frame, so that high-frequency details are clearer, and an image quality optimal result conforming to an online practical application scene is obtained, and therefore, a. A reconstructed video frame sequence with a second resolution can be generated according to the target reconstructed video frame, and cleaner, clearer, more natural and more comfortable video experience can be provided for users.

Description

technical field [0001] The present application relates to the field of image processing, in particular to an artificial intelligence-based super-resolution reconstruction method, device, device and storage medium. Background technique [0002] Image super-resolution refers to the technology of reconstructing a high-resolution image by processing one or more low-resolution images with complementary information, which is widely used in various media data (such as video or image) quality, such as online video viewing, medical imaging, video surveillance, remote sensing imaging and other fields. [0003] A super-resolution reconstruction method based on deep learning has been proposed in related technologies, but the generalization effect of the super-resolution reconstruction method in related technologies is poor. Facing real scenes online, the results obtained may not be the results with the best picture quality, often Satisfactory super-resolution effects cannot be obtained...

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): G06T3/40G06T5/00G06T11/00G06N3/04G06N3/08
CPCG06T3/4076G06T3/4007G06T5/002G06T11/001G06N3/08G06N3/045G06T3/4053G06T3/4046G06T2207/10016G06T2207/20081
Inventor 王茹李雅卿涂承杰熊诗尧江林燕彭龙涛
Owner TENCENT TECH (SHENZHEN) CO LTD
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