Self-supervised denoising for massive noisy images
Not on the map. Why?
Abstract (arXiv)
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-rAngstr"om resolution atomic images to sub-arcsecond resolution astronomy images.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 29 references that are in the map. First posted on arXiv 18 Oct 2021.
Builds on
13 of 29 references.
References · 13
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
- 2017Deep Neural Networks as Gaussian Processescited by 622
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
- 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 364
- 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
- 2018Residual Dense Network for Image Restorationcited by 181
- 2017Machine Learning Models that Remember Too Muchcited by 169
- 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
- 2019Deep Learning on Image Denoising: An overviewcited by 128
- 2020Every Model Learned by Gradient Descent Is Approximately a Kernel Machinecited by 55
Built on by
Not cited yet.