Noise2Noise: Learning Image Restoration without Clean Data

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 ICML 2018 PDF ICML 2018 Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Salt-And-Pepper Noise Removal BSD300 Noise Level 30% Noise2Noise PSNR 39.83 # 2
Salt-And-Pepper Noise Removal BSD300 Noise Level 50% Noise2Noise PSNR 35.92 # 2
Salt-And-Pepper Noise Removal BSD300 Noise Level 70% Noise2Noise PSNR 31.42 # 2
Salt-And-Pepper Noise Removal Kodak24 Noise Level 30% Noise2Noise PSNR 34.95 # 2
Salt-And-Pepper Noise Removal Kodak24 Noise Level 50% Noise2Noise PSNR 32.27 # 2
Salt-And-Pepper Noise Removal Kodak24 Noise Level 70% Noise2Noise PSNR 30.49 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet