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 sometimes 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, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans - all corrupted by different processes - based on noisy data only.
Cite
Text
Lehtinen et al. "Noise2Noise: Learning Image Restoration Without Clean Data." International Conference on Machine Learning, 2018.Markdown
[Lehtinen et al. "Noise2Noise: Learning Image Restoration Without Clean Data." International Conference on Machine Learning, 2018.](https://mlanthology.org/icml/2018/lehtinen2018icml-noise2noise/)BibTeX
@inproceedings{lehtinen2018icml-noise2noise,
title = {{Noise2Noise: Learning Image Restoration Without Clean Data}},
author = {Lehtinen, Jaakko and Munkberg, Jacob and Hasselgren, Jon and Laine, Samuli and Karras, Tero and Aittala, Miika and Aila, Timo},
booktitle = {International Conference on Machine Learning},
year = {2018},
pages = {2965-2974},
volume = {80},
url = {https://mlanthology.org/icml/2018/lehtinen2018icml-noise2noise/}
}