Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
Published in
International Conference on Learning Representa...(2020)External Links:
TL
TL;DR
DIVNOISING, a denoising approach based on fully convolutional variational autoencoders (VAEs), overcoming the problem of having to choose a single solution by predicting a whole distribution of denoised images by explicitly incorporating imaging noise models into the decoder.