DeepTreeGANv2: Iterative Pooling of Point Clouds

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Scham, Moritz Alfons Wilhelm, Krücker, Dirk, Borras, Kerstin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913182717575168
author Scham, Moritz Alfons Wilhelm
Krücker, Dirk
Borras, Kerstin
author_facet Scham, Moritz Alfons Wilhelm
Krücker, Dirk
Borras, Kerstin
contents In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, the generation of large point clouds in a short time is required, while the complex dependencies between the particles must be correctly modelled. Particle showers are inherently tree-based processes, as each particle is produced by the decay or detector interaction of a particle of the previous generation. In this work, we present a significant extension to DeepTreeGAN, featuring a critic, that is able to aggregate such point clouds iteratively in a tree-based manner. We show that this model can reproduce complex distributions, and we evaluate its performance on the public JetNet 150 dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2312_00042
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DeepTreeGANv2: Iterative Pooling of Point Clouds
Scham, Moritz Alfons Wilhelm
Krücker, Dirk
Borras, Kerstin
Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Experiment
In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, the generation of large point clouds in a short time is required, while the complex dependencies between the particles must be correctly modelled. Particle showers are inherently tree-based processes, as each particle is produced by the decay or detector interaction of a particle of the previous generation. In this work, we present a significant extension to DeepTreeGAN, featuring a critic, that is able to aggregate such point clouds iteratively in a tree-based manner. We show that this model can reproduce complex distributions, and we evaluate its performance on the public JetNet 150 dataset.
title DeepTreeGANv2: Iterative Pooling of Point Clouds
topic Data Analysis, Statistics and Probability
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2312.00042