DivNoising: Diversity Denoising with Fully Convolutional Variational Autoencoders

06/10/2020
by   Mangal Prakash, et al.
0

Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve the interpretability of acquired data. But there are limitations to what can be restored in corrupted images, and any given method needs to make a sensible compromise between many possible clean signals when predicting a restored image. Here, we propose DivNoising – a denoising approach based on fully-convolutional variational autoencoders, overcoming this problem by predicting a whole distribution of denoised images. Our method is unsupervised, requiring only noisy images and a description of the imaging noise, which can be measured or bootstrapped from noisy data. If desired, consensus predictions can be inferred from a set of DivNoising predictions, leading to competitive results with other unsupervised methods and, on occasion, even with the supervised state-of-the-art. DivNoising samples from the posterior enable a plethora of useful applications. We are (i) discussing how optical character recognition (OCR) applications could benefit from diverse predictions on ambiguous data, and (ii) show in detail how instance cell segmentation gains performance when using diverse DivNoising predictions.

READ FULL TEXT

page 18

page 19

page 23

page 25

page 26

page 28

page 31

page 34

research
10/12/2018

Cryo-CARE: Content-Aware Image Restoration for Cryo-Transmission Electron Microscopy Data

Multiple approaches to use deep learning for image restoration have rece...
research
09/18/2021

Removing Noise from Extracellular Neural Recordings Using Fully Convolutional Denoising Autoencoders

Extracellular recordings are severely contaminated by a considerable amo...
research
11/14/2016

Can fully convolutional networks perform well for general image restoration problems?

We present a fully convolutional network(FCN) based approach for color i...
research
11/27/2019

Leveraging Self-supervised Denoising for Image Segmentation

Deep learning (DL) has arguably emerged as the method of choice for the ...
research
11/27/2019

Fully Unsupervised Probabilistic Noise2Void

Image denoising is the first step in many biomedical image analysis pipe...
research
11/10/2020

Noise2Stack: Improving Image Restoration by Learning from Volumetric Data

Biomedical images are noisy. The imaging equipment itself has physical l...
research
06/06/2014

Analyzing noise in autoencoders and deep networks

Autoencoders have emerged as a useful framework for unsupervised learnin...

Please sign up or login with your details

Forgot password? Click here to reset