DeepAI AI Chat
Log In Sign Up

EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets

by   Erik Buhmann, et al.

With the vast data-collecting capabilities of current and future high-energy collider experiments, there is an increasing demand for computationally efficient simulations. Generative machine learning models enable fast event generation, yet so far these approaches are largely constrained to fixed data structures and rigid detector geometries. In this paper, we introduce EPiC-GAN - equivariant point cloud generative adversarial network - which can produce point clouds of variable multiplicity. This flexible framework is based on deep sets and is well suited for simulating sprays of particles called jets. The generator and discriminator utilize multiple EPiC layers with an interpretable global latent vector. Crucially, the EPiC layers do not rely on pairwise information sharing between particles, which leads to a significant speed-up over graph- and transformer-based approaches with more complex relation diagrams. We demonstrate that EPiC-GAN scales well to large particle multiplicities and achieves high generation fidelity on benchmark jet generation tasks.


page 10

page 14


3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions

In this paper, we propose a novel generative adversarial network (GAN) f...

Particle Cloud Generation with Message Passing Generative Adversarial Networks

In high energy physics (HEP), jets are collections of correlated particl...

PU-GAN: a Point Cloud Upsampling Adversarial Network

Point clouds acquired from range scans are often sparse, noisy, and non-...

A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds

In this paper, we introduce a novel conditional generative adversarial n...

Energy-Based Processes for Exchangeable Data

Recently there has been growing interest in modeling sets with exchangea...

Code Repositories


Pytorch implementation of the EPiC-GAN as introduced in

view repo