Noisier2Noise: Learning to Denoise From Unpaired Noisy Data

Nick Moran, Dan Schmidt, Yu Zhong, Patrick Coady; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12064-12072

Abstract


We present a method for training a neural network to perform image denoising without access to clean training examples or access to paired noisy training examples. Our method requires only a single noisy realization of each training example and a statistical model of the noise distribution, and is applicable to a wide variety of noise models, including spatially structured noise. Our model produces results which are competitive with other learned methods which require richer training data, and outperforms traditional non-learned denoising methods. We present derivations of our method for arbitrary additive noise, an improvement specific to Gaussian additive noise, and an extension to multiplicative Bernoulli noise.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moran_2020_CVPR,
author = {Moran, Nick and Schmidt, Dan and Zhong, Yu and Coady, Patrick},
title = {Noisier2Noise: Learning to Denoise From Unpaired Noisy Data},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}