A Method For Eliminating Contour Errors In Self-Encoder Reconstructed Images
This addresses image reconstruction quality issues in computer vision applications, but appears incremental as it builds on existing self-encoder and edge-based techniques.
The paper tackles contour errors in self-encoder reconstructed images by proposing a self-supervised twin network method that generates approximate edge information and uses a dilate algorithm to eliminate edge errors, improving reconstruction accuracy and separating foreign matter and noise for more practical visualization.
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