Noise2Noise: Learning image restoration without clean data

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Noise2Noise : Learning image restoration without clean data. / Lehtinen, Jaakko; Munkberg, Jacob; Hasselgren, Jon; Laine, Samuli; Karras, Tero; Aittala, Miika; Aila, Timo.

35th International Conference on Machine Learning, ICML 2018. ed. / Jennifer Dy; Andreas Krause. Vol. 7 2018. p. 4620-4631 (Proceedings of Machine Learning Research; No. 80).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Lehtinen, J, Munkberg, J, Hasselgren, J, Laine, S, Karras, T, Aittala, M & Aila, T 2018, Noise2Noise: Learning image restoration without clean data. in J Dy & A Krause (eds), 35th International Conference on Machine Learning, ICML 2018. vol. 7, Proceedings of Machine Learning Research, no. 80, pp. 4620-4631, International Conference on Machine Learning, Stockholm, Sweden, 10/07/2018.

APA

Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M., & Aila, T. (2018). Noise2Noise: Learning image restoration without clean data. In J. Dy, & A. Krause (Eds.), 35th International Conference on Machine Learning, ICML 2018 (Vol. 7, pp. 4620-4631). (Proceedings of Machine Learning Research; No. 80).

Vancouver

Lehtinen J, Munkberg J, Hasselgren J, Laine S, Karras T, Aittala M et al. Noise2Noise: Learning image restoration without clean data. In Dy J, Krause A, editors, 35th International Conference on Machine Learning, ICML 2018. Vol. 7. 2018. p. 4620-4631. (Proceedings of Machine Learning Research; 80).

Author

Lehtinen, Jaakko ; Munkberg, Jacob ; Hasselgren, Jon ; Laine, Samuli ; Karras, Tero ; Aittala, Miika ; Aila, Timo. / Noise2Noise : Learning image restoration without clean data. 35th International Conference on Machine Learning, ICML 2018. editor / Jennifer Dy ; Andreas Krause. Vol. 7 2018. pp. 4620-4631 (Proceedings of Machine Learning Research; 80).

Bibtex - Download

@inproceedings{68e7826482b3461a9bb8f230ddba1175,
title = "Noise2Noise: Learning image restoration without clean data",
abstract = "We apply basic statistical reasoning to signal reconstruction by machine learning - learning to map corrupted observations to clean signals - with a simple and powerful conclusion: It is possible to learn to restore images by only looking at corrupted examples, at performance at and some-times exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denois- ing synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only.",
author = "Jaakko Lehtinen and Jacob Munkberg and Jon Hasselgren and Samuli Laine and Tero Karras and Miika Aittala and Timo Aila",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "7",
series = "Proceedings of Machine Learning Research",
publisher = "PMLR",
number = "80",
pages = "4620--4631",
editor = "Jennifer Dy and Andreas Krause",
booktitle = "35th International Conference on Machine Learning, ICML 2018",

}

RIS - Download

TY - GEN

T1 - Noise2Noise

T2 - Learning image restoration without clean data

AU - Lehtinen, Jaakko

AU - Munkberg, Jacob

AU - Hasselgren, Jon

AU - Laine, Samuli

AU - Karras, Tero

AU - Aittala, Miika

AU - Aila, Timo

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We apply basic statistical reasoning to signal reconstruction by machine learning - learning to map corrupted observations to clean signals - with a simple and powerful conclusion: It is possible to learn to restore images by only looking at corrupted examples, at performance at and some-times exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denois- ing synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only.

AB - We apply basic statistical reasoning to signal reconstruction by machine learning - learning to map corrupted observations to clean signals - with a simple and powerful conclusion: It is possible to learn to restore images by only looking at corrupted examples, at performance at and some-times exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denois- ing synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only.

UR - http://www.scopus.com/inward/record.url?scp=85057221611&partnerID=8YFLogxK

M3 - Conference contribution

VL - 7

T3 - Proceedings of Machine Learning Research

SP - 4620

EP - 4631

BT - 35th International Conference on Machine Learning, ICML 2018

A2 - Dy, Jennifer

A2 - Krause, Andreas

ER -

ID: 31217122