Noise2Noise: Learning Image Restoration without Clean Data
Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Miika Aittala, Timo Aila
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/NVlabs/noise2noiseOfficialIn papertf★ 0
- github.com/Wenchao-Du/Neighbor2Neighbor_Pytorchpytorch★ 24
- github.com/joeylitalien/noise2noise-pytorchpytorch★ 0
- github.com/ishandutta2007/Image-Denoising-Landscapenone★ 0
- github.com/zzskyy0301/ML_PROJECTtf★ 0
- github.com/fanbeatsman/tensorflow-quick-start-image-processing-focus-tf★ 0
- github.com/ChungHanYang/Image-retoration-based-on-SRresnetpytorch★ 0
- github.com/foolish0/n2ntf★ 0
- github.com/shivamsaboo17/Deep-Restore-PyTorchpytorch★ 0
- github.com/vlcekl/n2n-tomopytorch★ 0
Abstract
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.