Unsupervised Cross Domain Learning for Noise Removal from a Single Image

Hong Xian Tsai, Li Wei Kang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Most supervised deep learning-based frameworks designed for image noise removal usually exhibit robust denoising performance depending on large scale clean/noisy paired training images. However, paired training data may be unavailable in several real scenarios. In recent, cross domain transferring has been applied to unsupervised learning for image restoration. To avoid possible domain shift problem in existing cross domain learning frameworks, in this paper, an unsupervised cross domain deep learning framework is proposed for noise removal from a single image. Our goal is to learn an image generator without paired training data to directly learn invariant feature representations from noisy images and generate the corresponding clean images. In our framework, we aim at learning two image generators to transfer noisy images to clean images as well as clean images to noisy images, respectively, denoted by noise-to-clean and clean-to-noise generators, based on unpaired training images. To train this cross domain learning model, we propose a generative adversarial network (GAN)-based network architecture with different types of discriminators and loss functions. As a result, both generators can be efficiently trained, and the learned noise-to-clean generator can robustly and effectively perform feature learning from input noisy images and produce the corresponding denoised images.

Original languageEnglish
Title of host publicationIST 2022 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665481021
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Conference on Imaging Systems and Techniques, IST 2022 - Virtual, Online, Taiwan
Duration: 2022 Jun 212022 Jun 23

Publication series

NameIST 2022 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

Conference

Conference2022 IEEE International Conference on Imaging Systems and Techniques, IST 2022
Country/TerritoryTaiwan
CityVirtual, Online
Period2022/06/212022/06/23

Keywords

  • cross domain learning
  • deep learning
  • image denoising
  • noise removal
  • unsupervised learning

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Unsupervised Cross Domain Learning for Noise Removal from a Single Image'. Together they form a unique fingerprint.

Cite this