A Method For Eliminating Contour Errors In Self-Encoder Reconstructed Images

TL;DR

This paper introduces a self-supervised twin network method that enhances image reconstruction accuracy by eliminating contour errors and separating noise, improving visualization in practical applications.

Contribution

It presents a novel self-supervised twin network approach utilizing edge information and dilation algorithms to reduce contour errors in reconstructed images.

Findings

Significant reduction in contour errors in reconstructed images

Effective separation of noise and foreign matter from original images

Improved visualization quality in practical scenarios

Abstract

In this paper, we propose a self-supervised twin network approach based on this a priori. The method of generating the approximate10 edge information of an image and then differentially eliminating the edge errors11 in the reconstructed image with a dilate algorithm. This is used to improve the12 accuracy of the reconstructed image and to separate foreign matter and noise from13 the original image, so that it can be visualized in a more practical scene