Diffusion models for super-resolution microscopy: a tutorial

• Published in: JPhys photonics Vol. 7; no. 1; pp. 13001 - 13035
• Main Authors: Bachimanchi, Harshith, Volpe, Giovanni
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 31.01.2025
• Subjects: Atom and Molecular Physics and Optics; Atom- och molekylfysik och optik; Background noise; deep learning; denoising diffusion probabilistic models (DDPMs); diffusion models; Image resolution; Microscopy; microscopy image enhancement; Neural networks; Noise levels; Probabilistic models; python tutorial; super-resolution
• ISSN: 2515-7647; 2515-7647
• DOI: 10.1088/2515-7647/ada101

Diffusion models have emerged as a prominent technique in generative modeling with neural networks, making their mark in tasks like text-to-image translation and super-resolution. In this tutorial, we provide a comprehensive guide to build denoising diffusion probabilistic models from scratch, with a specific focus on transforming low-resolution microscopy images into their corresponding high-resolution versions in the context of super-resolution microscopy. We provide the necessary theoretical background, the essential mathematical derivations, and a detailed Python code implementation using PyTorch. We discuss the metrics to quantitatively evaluate the model, illustrate the model performance at different noise levels of the input low-resolution images, and briefly discuss how to adapt the tutorial for other applications. The code provided in this tutorial is also available as a Python notebook in the supplementary information.