Noisier2Noise: Learning to Denoise From Unpaired Noisy Data
By Nick Moran, Dan Schmidt, Yu Zhong, Patrick Coady. Computer Vision and Pattern Recognition, 2019
318 citations recorded by the source corpus.
We present a method for training a neural network to perform image denoising without access to clean training examples or access to paired noisy training examples. Our method requires only a single noisy realization of each training example and a statistical model of the noise distribution, and is applicable to a wide variety of noise models, including spatially structured noise. Our model produces results which are competitive with other learned methods which require richer training data, and outperforms traditional non-learned denoising methods. We present derivations of our method for arbitrary additive noise, an improvement specific to Gaussian additive noise, and an extension to multiplicative Bernoulli noise.
Subfields: Biophysics, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/3106671680dc238d11c9655d2075e37a5e8ef649
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biophysics
In Computer Vision and Pattern Recognition
- Huchuan Lu
- Xu Jia
- Jian-zhuo Liu
- Songjiang Li
- Tao Huang
- Ming-Hsuan Yang
- Luc Van Gool
- Fahad Shahbaz Khan
Citations in the corpus
- Isotropic reconstruction for electron tomography with deep learning (2022, methodology): “Within the Re fi ne step of IsoNet, we alsoimplemented a denoising module based on the noisier-input strategy 42,43 .”
- Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images (2021, methodology): “…Neighbor2Neighbor against two baseline methods (supervised de-noising (N2C) and Noise2Noise (N2N) [17]), one traditional image denoiser (BM3D [7]), and five self-supervised image denoising methods (Deep Image Prior (DIP) [29], Noise2Void (N2V) [13], Laine19 [15], Noisier2Noise [22] and DBSN [30]).”