NODE-ImgNet : a PDE-informed effective and robust model for image denoising

Xie, Xinheng and Wu, Yue and Ni, Hao and He, Cuiyu (2024) NODE-ImgNet : a PDE-informed effective and robust model for image denoising. Pattern Recognition, 148. 110176. ISSN 0031-3203 (https://doi.org/10.1016/j.patcog.2023.110176)

[thumbnail of Xie-etal-PR-2023-NODE-ImgNet-a-PDE-informed-effective] Text. Filename: Xie-etal-PR-2023-NODE-ImgNet-a-PDE-informed-effective.pdf
Accepted Author Manuscript
Restricted to Repository staff only until 6 December 2024.
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (13MB) | Request a copy

Abstract

Inspired by the traditional partial differential equation (PDE) approach for image denoising, we propose a novel neural network architecture, referred as NODE-ImgNet, that combines neural ordinary differential equations (NODEs) with convolutional neural network (CNN) blocks. NODE-ImgNet is intrinsically a PDE model, where the dynamic system is learned implicitly without the explicit specification of the PDE. This naturally circumvents the typical issues associated with introducing artifacts during the learning process. By invoking such a NODE structure, which can also be viewed as a continuous variant of a residual network (ResNet) and inherits its advantage in image denoising, our model achieves enhanced accuracy and parameter efficiency. In particular, our model exhibits consistent effectiveness in different scenarios, including denoising gray and color images perturbed by Gaussian noise, as well as real-noisy images, and demonstrates superiority in learning from small image datasets.

  • Item type:Article
    ID code:87653
    Dates:
    Date
    Event
    April 2024
    Published
    6 December 2023
    Published Online
    28 November 2023
    Accepted
    Subjects:Science > Mathematics
    Department:Faculty of Science > Mathematics and Statistics
    Depositing user: Pure Administrator
    Date deposited:18 Dec 2023 10:41
    Last modified:11 Nov 2024 14:10
    URI:https://strathprints.strath.ac.uk/id/eprint/87653
CORE (COnnecting REpositories)