Denoising in 2D (human U2OS data)


This example is part of the CSBDeep framework. The method is described in Content-aware image restoration: pushing the limits of fluorescence microscopy by Martin Weigert et al. and the data are Human U2OS cells taken from the Broad Bioimage Benchmark Collection.


The low SNR images were created by synthetically adding strong read-out and shot-noise (and additionally applying pixel binning of 2x2) thus mimicking acquisitions at a very low light level.


To reproduce this example follow the instructions in this jupyter notebook.