SRFormer: a 3-D Image SR Backbone Network

We develop Lattice light sheet Activation Structured Illumination Microscopy (LA-SIM) which allows implementing rationalized deep-learning (rDL) denoising in a self-supervised manner and enables producing high-quality three-dimensional (3-D) SR images at limited SNR levels. We utilize the high-quality rDL LA-SIM data to train a large-scale transformer model --- SRFormer that can overcome the inferior properties of rsFPs and enable multi-color long-term volumetric SR imaging. We have provided demo data and pretrained model of SRFormer here. You can get more details about tutorial of the implementation of SRFormer from our Github.