TY - GEN
T1 - Unsupervised Cross Domain Learning for Noise Removal from a Single Image
AU - Tsai, Hong Xian
AU - Kang, Li Wei
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - cross domain learning
KW - deep learning
KW - image denoising
KW - noise removal
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85135959637&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135959637&partnerID=8YFLogxK
U2 - 10.1109/IST55454.2022.9827766
DO - 10.1109/IST55454.2022.9827766
M3 - Conference contribution
AN - SCOPUS:85135959637
T3 - IST 2022 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
BT - IST 2022 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Imaging Systems and Techniques, IST 2022
Y2 - 21 June 2022 through 23 June 2022
ER -