How to do Physics-based Learning

TL;DR

This paper provides a step-by-step tutorial on implementing physics-based learning for computational imaging, emphasizing auto-differentiation and offering an open-source PyTorch toolkit for rapid prototyping.

Contribution

It introduces a practical methodology for physics-based learning, simplifying implementation through auto-differentiation and providing an open-source framework for sparse recovery problems.

Findings

Open-source PyTorch implementation available

Accelerates prototyping of physics-based imaging systems

Demonstrates effectiveness on sparse recovery tasks

Abstract

The goal of this tutorial is to explain step-by-step how to implement physics-based learning for the rapid prototyping of a computational imaging system. We provide a basic overview of physics-based learning, the construction of a physics-based network, and its reduction to practice. Specifically, we advocate exploiting the auto-differentiation functionality twice, once to build a physics-based network and again to perform physics-based learning. Thus, the user need only implement the forward model process for their system, speeding up prototyping time. We provide an open-source Pytorch implementation of a physics-based network and training procedure for a generic sparse recovery problem