Jet Image Generation in High Energy Physics Using Diffusion Models

TL;DR

This paper introduces the first application of diffusion models to generate realistic jet images for high energy physics, improving fidelity and efficiency over previous methods.

Contribution

It demonstrates the use of diffusion models directly in image space for class-conditional jet image generation, a novel approach in HEP.

Findings

Consistency models outperform score-based diffusion models in image fidelity.

Generated jet images achieve lower FID scores, indicating higher quality.

The method enhances computational efficiency and accuracy in jet image simulation.

Abstract

This article presents, for the first time, the application of diffusion models for generating jet images corresponding to proton-proton collision events at the Large Hadron Collider (LHC). The kinematic variables of quark, gluon, W-boson, Z-boson, and top quark jets from the JetNet simulation dataset are mapped to two-dimensional image representations. Diffusion models are trained on these images to learn the spatial distribution of jet constituents. We compare the performance of score-based diffusion models and consistency models in accurately generating class-conditional jet images. Unlike approaches based on latent distributions, our method operates directly in image space. The fidelity of the generated images is evaluated using several metrics, including the Fr\'echet Inception Distance (FID), which demonstrates that consistency models achieve higher fidelity and generation stability compared to score-based diffusion models. These advancements offer significant improvements in computational efficiency and generation accuracy, providing valuable tools for High Energy Physics (HEP) research.