Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images

Simple item page
dc.contributor.advisorBrown, Michael S.
dc.contributor.authorMaleky, Ali
dc.date.accessioned2022-12-14T16:36:32Z
dc.date.available2022-12-14T16:36:32Z
dc.date.copyright2022-08-11
dc.date.issued2022-12-14
dc.date.updated2022-12-14T16:36:32Z
dc.degree.disciplineElectrical and Computer Engineering
dc.degree.levelMaster's
dc.degree.nameMASc - Master of Applied Science
dc.description.abstractImage noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model (a.k.a., camera noise level function) are not sufficient to learn the complex behavior of the camera sensor noise. Recently, more complex learning-based models have been proposed that yield better results in noise synthesis and downstream tasks, such as denoising. However, their dependence on supervised data (i.e., paired clean images) is a limiting factor given the challenges in producing ground-truth images. This paper proposes a framework for training a noise model and a denoiser simultaneously while relying only on pairs of noisy images rather than noisy/clean paired image data. We apply this framework to the training of the Noise Flow architecture. The noise synthesis and density estimation results show that our framework outperforms previous signal-processing-based noise models and is on par with its supervised counterpart. The trained denoiser is also shown to significantly improve upon both supervised and weakly supervised baseline denoising approaches. The results indicate that the joint training of a denoiser and a noise model yields significant improvements in the denoiser.
dc.identifier.urihttp://hdl.handle.net/10315/40727
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subjectArtificial intelligence
dc.subject.keywordsMachine learning
dc.subject.keywordsComputer vision
dc.subject.keywordsComputational photography
dc.subject.keywordsCamera image
dc.subject.keywordsImage noise
dc.subject.keywordsGenerative models
dc.subject.keywordsDeep unsupervised learning
dc.subject.keywordsNoise model
dc.subject.keywordsDenoiser
dc.subject.keywordsNoise reduction
dc.titleNoise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Maleky_Ali_2022_Masters.pdf
Size:
5.13 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Electrical and Computer Engineering

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.