This work (method and data) is part of Content-aware image restoration: pushing the limits of fluorescence microscopy by Martin Weigert et al. in Nature Methods.
Finally we show an example where neither the real biological ground-truth nor the real image degradation process is experimentally accessible, but a synthetic generative model of image content and image degradation process is available.
The predictions of a CARE Network trained on fully synthetic training data shows that wide-field acquisitions can yield high-quality reconstructions.
The trained model is published for demonstration purposes. You can try it via Fiji and KNIME.
To run the demo in Fiji, follow these instructions.
To run the demo in KNIME, follow these instructions.
Reconstruction of diffraction-limited structures at very high frame-rate in rat insulin secretory granules.
Reconstruction of diffraction-limited microtubules at very high frame-rate in HeLa cells.