Self-supervised denoising for massive noisy images

Abstract

We propose an effective deep learning model for signal reconstruction, which requires no signal prior, no noise model calibration, and no clean samples. This model only assumes that the noise is independent of the measurement and that the true signals share the same structured information. We demonstrate its performance on a variety of real-world applications, from sub-Ångström resolution atomic images to sub-arcsecond resolution astronomy images.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
• Multi-scale Convolutional Neural Networks for Inverse Problems
• Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
• This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces