Point-cloud generative models for fast calorimeter simulation across particles and geometries
Abstract
Detailed Geant4 simulation of calorimeter showers is the largest single computing cost of collider experiments, and the High-Luminosity LHC will need about ten times more simulated events than are currently produced. We summarise recent progress in generative point cloud fast simulation for highly granular calorimeters. CaloClouds3 generates photon (electromagnetic) showers, is geometry-independent, and runs on average about 120x faster than Geant4 on a single CPU. CaloHadronic uses transformer attention to extend the point cloud diffusion approach to pion (hadronic) showers spanning the electromagnetic and hadronic calorimeters. AllShowers unifies twelve particle types in a single model with far fewer parameters than the specialised baselines while matching or exceeding their fidelity. We close with cross-geometry transfer learning, which needs two to three orders of magnitude fewer training showers while preserving the generative performance.
Related
- Statistical validation of calorimeter inpainting with generative diffusion priors
- Design and Simulation Study of the Hadronic Calorimeter for the EicC Zero Degree Calorimeter
- A Coherent Memory Register for Sequential Quantum Generative Modeling, with Application to Calorimeter Showers
- HybridMC: a fast detailed simulation framework for optical calorimeter technologies at the LHCb ECAL Upgrade II
- A non-uniform local reference frame method for the simulation of rotating geometries with non-conformal grids on the hybrid recursive regularized lattice Boltzmann method
BibTeX
@misc{buss2026pointcloud,
title = {{Point-cloud generative models for fast calorimeter simulation across particles and geometries}},
author = {Thorsten Buss and Henry Day-Hall and Frank Gaede and Gregor Kasieczka and Katja Krüger and Anatolii Korol and Thomas Madlener and Peter McKeown and Martina Mozzanica and Lorenzo Valente},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.30403},
eprint = {2609.30403},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30403},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Point-cloud generative models for fast calorimeter simulation across particles and geometries
AU - Thorsten Buss
AU - Henry Day-Hall
AU - Frank Gaede
AU - Gregor Kasieczka
AU - Katja Krüger
AU - Anatolii Korol
AU - Thomas Madlener
AU - Peter McKeown
AU - Martina Mozzanica
AU - Lorenzo Valente
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.30403
UR - https://arxiv.org/abs/2609.30403
AB - Detailed Geant4 simulation of calorimeter showers is the largest single computing cost of collider experiments, and the High-Luminosity LHC will need about ten times more simulated events than are currently produced. We summarise recent progress in generative point cloud fast simulation for highly granular calorimeters. CaloClouds3 generates photon (electromagnetic) showers, is geometry-independent, and runs on average about 120x faster than Geant4 on a single CPU. CaloHadronic uses transformer attention to extend the point cloud diffusion approach to pion (hadronic) showers spanning the electromagnetic and hadronic calorimeters. AllShowers unifies twelve particle types in a single model with far fewer parameters than the specialised baselines while matching or exceeding their fidelity. We close with cross-geometry transfer learning, which needs two to three orders of magnitude fewer training showers while preserving the generative performance.
ER -