It could allow direct segmentation of super resolved features in fully automated and user-friendly settings.
Merged super resolved structures might show intensity variation throughout the whole object, because each of the merged clusters has different intensity profile.
Image segmentation algorithms that use shape or intensity data will identify single super resolved clusters, but will not perceive a group of separate clusters as one functionally active domain.
Interestingly, expanding Gaussian diameter by a factor more than the resolution of super resolved gp210 clusters, we were able to merge adjacent gp210 subunits of nuclear pore complex into donut structure (Fig. 2b).
We can iteratively super-resolve the frames as in previous works [16 18, 28] by replacing the operation just described.
In the future, we will also investigate extending our proposed anchored neighborhood deep network into a spatio-temporal network to super-resolve one frame from multiple neighboring frames.
To overcome the blocking artifacts and deal with the case of small structures with large displacement, an efficient method based on feature-guided variational optical flow is used to super-resolve the non-key-frames.
The design of pupil phase filters that super-resolve the axial intensity distribution with controlled side-lobe peak intensity under high numerical aperture conditions can be accomplished by incorporating the theory of electromagnetic diffraction in the method of generalized projections (MGP).
Finally, ZEMAX software was used to simulate the whole super-resolving system.
(c, g) Super-resolved by a factor of four with the methods in [8, 23].
This clustering mechanism, along with the mapping function paradigm, allows us to super-resolve patches with high-frequency components.
