Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC

TL;DR

This paper introduces a novel approach using instance segmentation GNNs in conformal geometry to improve particle tracking at the LHC, enabling single-shot track identification and parameter extraction from detector hit data.

Contribution

It demonstrates the application of GNN-based instance segmentation in conformal space for particle tracking, offering a new geometric perspective and streamlined processing.

Findings

GNNs effectively identify particle tracks in conformal space.

Single-shot track parameter extraction is achieved.

The approach outperforms traditional Cartesian methods.

Abstract

3D instance segmentation remains a challenging problem in computer vision. Particle tracking at colliders like the LHC can be conceptualized as an instance segmentation task: beginning from a point cloud of hits in a particle detector, an algorithm must identify which hits belong to individual particle trajectories and extract track properties. Graph Neural Networks (GNNs) have shown promising performance on standard instance segmentation tasks. In this work we demonstrate the applicability of instance segmentation GNN architectures to particle tracking; moreover, we re-imagine the traditional Cartesian space approach to track-finding and instead work in a conformal geometry that allows the GNN to identify tracks and extract parameters in a single shot.