Image Denoising with Stochastic Differential Equations
Title: Image Denoising with Stochastic Differential Equations
DNr: Berzelius-2024-188
Project Type: LiU Berzelius
Principal Investigator: Ziwei Luo <ziwei.luo@it.uu.se>
Affiliation: Uppsala universitet
Duration: 2024-06-01 – 2024-12-01
Classification: 10207
Homepage: https://algolzw.github.io/
Keywords:

Abstract

The Wiener process is to add continuous Gaussian noises to a clean signal, which constructs the dispersion part of a Stochastic Differential Equation (SDE). In this project, we model the image noise-adding process as a conditional Wiener process where the noisy image is an intermediate state and the transition follows a simple SDE. Naturally, we can reverse the SDE to get the initial state image. Its drift function of the reverse-time SDE can be derived from the original forward SDE with an additional score function which can be approximated with a deep convolutional neural network (CNN). This project aims to breakthrough the current frameworks of image denoising, leading to a better result in realistic image/signal restoration.