Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Noise2Self: Blind Denoising by Self-Supervision

About

We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only assumption is that the noise exhibits statistical independence across different dimensions of the measurement, while the true signal exhibits some correlation. For a broad class of functions ("$\mathcal{J}$-invariant"), it is then possible to estimate the performance of a denoiser from noisy data alone. This allows us to calibrate $\mathcal{J}$-invariant versions of any parameterised denoising algorithm, from the single hyperparameter of a median filter to the millions of weights of a deep neural network. We demonstrate this on natural image and microscopy data, where we exploit noise independence between pixels, and on single-cell gene expression data, where we exploit independence between detections of individual molecules. This framework generalizes recent work on training neural nets from noisy images and on cross-validation for matrix factorization.

Joshua Batson, Loic Royer• 2019

Related benchmarks

TaskDatasetResultRank
Image DenoisingSIDD (val)
PSNR30.72
105
Image DenoisingDND
PSNR33.63
99
Image DenoisingSIDD (test)
PSNR30.98
97
Image DenoisingCBSD68 (test)
PSNR33.18
92
Gaussian DenoisingBSD68
PSNR28.28
89
Poisson Image DenoisingBSD68
PSNR31.04
61
Image DenoisingSIDD Benchmark
PSNR32.57
61
Image DenoisingCBSD68 synthetic Gaussian (test)
PSNR32.88
56
Gaussian DenoisingSet12
Average PSNR29.16
47
Image DenoisingCBSD68 sigma=25 (test)
PSNR30.99
46
Showing 10 of 71 rows
...

Other info

Follow for update