Unsupervised Image Restoration Using Partially Linear Denoisers.
IEEE transactions on pattern analysis and machine intelligence
MetadataShow full item record
Ke, R., & Schonlieb, C. (2021). Unsupervised Image Restoration Using Partially Linear Denoisers.. IEEE transactions on pattern analysis and machine intelligence, PP https://doi.org/10.1109/tpami.2021.3070382
Standard supervised learning frameworks for image restoration require a set of noisy measurement and clean image pairs for which a distance between the output of the restoration model and the ground truth images is minimized. The ground truth images, however, are often unavailable or very expensive to acquire in real-world applications. We circumvent this problem by proposing a class of structured denoisers that can be decomposed as the sum of a nonlinear image-dependent mapping, a linear noise-dependent term and a small residual term. We show that these denoisers can be trained with only noisy images under the condition that the noise has zero mean and known variance. The exact distribution of the noise, however, is not assumed to be known. We show the superiority of our approach for image denoising, and demonstrate its extension to solving other restoration problems such as blind deblurring where the ground truth is not available. Our method outperforms some recent unsupervised and self-supervised deep denoising models that do not require clean images for their training. For blind deblurring problems, the method, using only one noisy and blurry observation per image, reaches a quality not far away from its fully supervised counterparts on a benchmark dataset.
European Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (691070)
Alan Turing Institute (unknown)
European Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (777826)
Leverhulme Trust (RPG-2018-121)
Leverhulme Trust (PLP-2017-275)
Alan Turing Institute (Unknown)
Royal Society (RSWF\R3\193016)
External DOI: https://doi.org/10.1109/tpami.2021.3070382
This record's URL: https://www.repository.cam.ac.uk/handle/1810/321616
All rights reserved