Unlock instant, AI-driven research and patent intelligence for your innovation.

Image restoration method based on LSK-FNet model

A repair method and image technology, applied in the field of image repair, can solve problems such as unreasonable semantic understanding, blurred edge structure, visual artifacts, etc.

Pending Publication Date: 2021-12-17
CHONGQING NORMAL UNIVERSITY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image repair method based on the LSK-FNet model, aiming to solve the blurred edge structure, excessive smoothing, unreasonable semantic understanding, visual artifacts and repair effects of the repaired image in the prior art. poor technical problem

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
  • Image restoration method based on LSK-FNet model
  • Image restoration method based on LSK-FNet model
  • Image restoration method based on LSK-FNet model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0037] In describing the present invention, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", The orientation or positional relationship indicated by "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than Nothing indicating or implying that a referenced device or element...

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 relates to the technical field of image restoration, and particularly discloses an image restoration method based on an LSK-FNet model, and the method comprises the steps: constructing and training an edge generation network; constructing and training an image restoration network; combining the edge generation network and the image restoration network to form an end-to-end LSK-FNet model, and training the LSK-FNet model; and repairing the face image by using the LSK-FNet model. The image restoration work is divided into two steps through an LSK-FNet model: using an edge generation network to generate restored edge information as prior information of subsequent image restoration; putting the generated prior information and the damaged original image into an image restoration network together for restoration; fusing the gated convolution into the whole generative adversarial network to perform training, and adopting region normalization in the image restoration network to improve restoration details and accuracy, so the phenomena of fuzzy edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts of the restored image are avoided, and the image restoration effect is improved.

Description

technical field [0001] The invention relates to the technical field of image restoration, in particular to an image restoration method based on an LSK-FNet model. Background technique [0002] Image inpainting technology is based on the known information of the undamaged area of ​​the image to repair the missing area in the image, so that it is reasonable to see the repaired image subjectively, and maintain the coherence of the overall structure of the image to meet the visual continuity. Algorithm that is consistent with the current image scene. [0003] Existing image restoration uses generative confrontation networks and attention mechanisms to increase the semantic understanding between the various elements of the face, but the edge structure of the repaired image is blurred, over-smooth, unreasonable semantic understanding, and visual artifacts. The restoration is poor. Contents of the invention [0004] The purpose of the present invention is to provide an image re...

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): G06T5/00G06T7/00G06T7/13G06N3/04G06N3/08
CPCG06T7/0002G06T7/13G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30201G06N3/045G06T5/00
Inventor 杨有刘思汛李可森余平杨学森
Owner CHONGQING NORMAL UNIVERSITY