We report a three-dimensional target-locking-based single-molecule fluorescence Spectrum Dynamics Imaging Microscopy (3D-SpecDIM), a method capable of simultaneously capturing both rapid 3D positional dynamics and physicochemical parameter changing dynamics.
Deep Learning models poses a signifcant challenge for real-world applications, where unknown diffusionmodels are common. We present a general framework for evaluating deep-learning-based out-of-distribution (OOD) dynamics-detection methods.
We propose a deep learning-enhanced single-molecule spectrum imaging method (SpecGAN) for improving the single-molecule spectrum imaging efficiency.
