Extending Stein's unbiased risk estimator to train deep denoisers with correlated pairs of noisy images
proceedings.neurips.cc · 5,942 words · saved by 1 readers
N/A
Extending Stein’s unbiased risk estimator to train deep denoisers with correlated pairs of noisy images Magauiya Zhussip Shakarim Soltanayev Se Young Chun Ulsan National Institute of Science and Technology (UNIST) {mzhussip, shakarim, sychun}@unist.ac.kr Abstract Recently, Stein’s unbiased risk estimator (SURE) has been applied to unsupervised training of deep neural network Gaussian denoisers that outperformed classical non-deep learning…
saved by
related reading
- Unsupervised Learning with SURE.pdfarxiv.org
- Noiser2Noise.pdfarxiv.org
- Noise2Scoreproceedings.neurips.cc
- Neighbor2Neighborarxiv.org
- [2007.13640] Solving Linear Inverse Problems Using the Prior Implicit in a Denoiserarxiv.org
- generalized surearxiv.org
- Denoising Density Estimatorsarxiv.org
- Regularized by Score Matching (LeCun)papers.nips.cc
- Beyond Gaussian Noise: A Generalized Approach to Likelihood Analysis with Non-Gaussian Noiseiopscience.iop.org
- Deep Energy Estimator.pdfarxiv.org
- empirical_bayes_without_prior_or_supervision_raphan.pdfcns.nyu.edu
- The Little Book of Deep Learningfleuret.org