Homepage: https://cabooster.github.io/DeepCAD-RT/

Code: https://github.com/cabooster/DeepCAD-RT

Dataset: https://cabooster.github.io/DeepCAD-RT/Datasets/

The code, tutorial, and dataset have been released publicly. Denoising networks can be trained by the original low-SNR data without requiring any high-SNR or ground-truth data. It is particularly advantageous in scenarios where the sample is undergoing fast dynamics and capturing ground-truth data is hard or impossible.