Noisier2Noise: Learning to Denoise from Unpaired Noisy Data

TL;DR

This paper introduces a novel neural network training method for image denoising that learns from unpaired noisy data using only a single noisy example per training instance and a noise model, outperforming traditional methods.

Contribution

It presents a new approach to train denoising models without clean or paired noisy data, applicable to various noise types including structured noise.

Findings

Achieves competitive denoising results with minimal training data.

Outperforms traditional non-learned denoising techniques.

Extends to multiple noise models including Gaussian and Bernoulli.

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.