A data-driven algorithm for solving image despeckling PDE model using physics-informed ConvNet

In this study, we propose a new data-driven algorithm for the Perona-Malik image despeckling problem. The advantage of the proposed algorithm over neural network-based methods is that it does not need any noisy and clean image data pair for training. The proposed algorithm is implemented using a thr...

Full description

Bibliographic Details

Published in:	Computers & mathematics with applications (1987) Vol. 200; pp. 202 - 227
Main Authors:	Kumar, Haridarshan, Kumar, Sanjeev
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 15.12.2025
Subjects:	Convolutional neural networks Diffusion Finite difference method Image despeckling PDEs Physics-informed machine learning Physics-informed machine learning Convolutional neural networks Diffusion Image despeckling PDEs Finite difference method
ISSN:	0898-1221
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!