Dataset and trained models for video denoising in fluorescence guided surgery

Fluorescence guided surgery (FGS) is a promising surgical
technique that gives surgeons a unique view of tissue that is
used to guide their practice by delineating tissue types
and diseased areas. As new fluorescent contrast agents are
developed that have low fluorescent photon yields, it becomes
increasingly important to develop computational models to allow
FGS systems to maintain good video quality in real time
environments. To further complicate this task, FGS has a
difficult bias noise term from laser leakage light (LLL) that
represents unfiltered excitation light that can be on the order
of the fluorescent signal. This dataset contains the data used to
develop and train video denoising models for fluroescence guided surgery
with LLL. This dataset contains bright fluorescence data in a mock chicken
thigh surgery for FGS video simulation, non-fluorescent video for LLL
simulation, as well as a number of calibration datasets for properly
simulating a comercial system, and real noise video for testing. We also
provide result videos of our denoising models trained with this data and
the trained models.