Comparison of Point Cloud and Image-based Models for Calorimeter Fast Simulation

TL;DR

This paper compares point cloud and image-based score generative models for calorimeter simulation, highlighting the advantages of point clouds in preserving information and handling sparsity.

Contribution

It presents a direct comparison of state-of-the-art score-based models using point cloud and image representations for calorimeter data.

Findings

Point cloud models better preserve original data details.

Point clouds handle sparse datasets more naturally.

Comparison shows strengths and weaknesses of each approach.

Abstract

Score based generative models are a new class of generative models that have been shown to accurately generate high dimensional calorimeter datasets. Recent advances in generative models have used images with 3D voxels to represent and model complex calorimeter showers. Point clouds, however, are likely a more natural representation of calorimeter showers, particularly in calorimeters with high granularity. Point clouds preserve all of the information of the original simulation, more naturally deal with sparse datasets, and can be implemented with more compact models and data files. In this work, two state-of-the-art score based models are trained on the same set of calorimeter simulation and directly compared.