Xie, Xinheng; Wu, Yue; Ni, Hao; He, Cuiyu; (2024) NODE-ImgNet: A PDE-informed effective and robust model for image denoising. Pattern Recognition , 148 , Article 110176. 10.1016/j.patcog.2023.110176.

Text 1-s2.0-S0031320323008737-main.pdf - Accepted Version Access restricted to UCL open access staff until 20 December 2024. Download (14MB)

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.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item