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

Xinheng Xie, Yue Wu, Hao Ni, Cuiyu He

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

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.
Original languageEnglish
Article number110176
Number of pages29
JournalPattern Recognition
Volume148
Early online date6 Dec 2023
DOIs
Publication statusPublished - Apr 2024

Keywords

  • partial differential equation
  • neural network architecture
  • image denoising

Fingerprint

Dive into the research topics of 'NODE-ImgNet: a PDE-informed effective and robust model for image denoising'. Together they form a unique fingerprint.

Cite this