NODE-ImgNet: a PDE-informed effective and robust model for image denoising
This is an incremental improvement for image processing, offering a robust model that works well with small datasets.
The authors tackled image denoising by proposing NODE-ImgNet, a neural network combining neural ODEs with CNNs to implicitly learn PDE dynamics, achieving enhanced accuracy and parameter efficiency across gray/color images with Gaussian noise and real-noisy images.
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.