A U-Net with separate signal and noise branches and signal-plus-whiteness-prior losses denoises confocal endomicroscopy images without clean training data, beating Noise2Self, BM3D, and NLM on synthetic AWGN tests.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
WhiteNNer-Blind Image Denoising via Noise Whiteness Priors
A U-Net with separate signal and noise branches and signal-plus-whiteness-prior losses denoises confocal endomicroscopy images without clean training data, beating Noise2Self, BM3D, and NLM on synthetic AWGN tests.