We present a machine learning-assisted approach for the realization of rapid antibunching super-resolution microscopy and demonstrate 12 times speed-up compared to conventional, fitting-based autocorrelation measurements.
The developed framework paves the way to the practical realization of scalable quantum super-resolution imaging devices that can be compatible with various types of quantum emitters.
Super-resolution microscopy is a novel technique that enables the pinpointing of fluorophores either directly during the experiment or postexperimentally using a sequence of acquired sparse image frames.
The resulting list of fluorophore coordinates is utilized to produce high-resolution images or to gain quantitative insight into the underlying biological structures.
In this paper, the performance of a convolutional neural network architecture known as u-net for foreground super resolution combined with maskregion based cnn (mr-cnn) for foreground super resolution is analysed.
This analysis is carried out based on localized super resolution i.e.
We present a special issue covering the various aspects of structural illumination microscopy, from bespoke hardware and software development and the use of commercial instruments to biological applications.
We also discuss complementary super-resolution microscopytechniques, computational imaging, visualisation and image processing methods.