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)
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: 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: DateEventApril 2024Published6 December 2023Published Online28 November 2023AcceptedSubjects: Science > Mathematics Department: Faculty of Science > Mathematics and Statistics Depositing user: Pure Administrator Date deposited: 18 Dec 2023 10:41 Last modified: 01 Oct 2024 01:25 URI: https://strathprints.strath.ac.uk/id/eprint/87653