Noise2Noise: Learning Image Restoration without Clean Data

ICML 2018 Jaakko LehtinenJacob MunkbergJon HasselgrenSamuli LaineTero KarrasMiika AittalaTimo Aila

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...

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Color Image Denoising BSD300 sigma30 Noise2Noise PSNR 39.83 # 2
Color Image Denoising BSD300 sigma50 Noise2Noise PSNR 35.92 # 2
Color Image Denoising BSD300 sigma70 Noise2Noise PSNR 31.42 # 2
Color Image Denoising Kodak24 sigma30 Noise2Noise PSNR 34.95 # 2
Color Image Denoising Kodak24 sigma50 Noise2Noise PSNR 32.27 # 2
Color Image Denoising Kodak24 sigma70 Noise2Noise PSNR 30.49 # 2