Unpaired Translation of Point Clouds for Modeling Detector Response
This addresses noise rejection and simulator fidelity for particle physics experiments, but is incremental as it builds on existing diffusion models.
The paper tackled modeling detector response in time projection chambers by framing it as an unpaired point cloud translation task between simulation and experimental data, achieving success in synthetic domains and real data from the Active-Target Time Projection Chamber.
Modeling detector response is a key challenge in time projection chambers. We cast this problem as an unpaired point cloud translation task, between data collected from simulations and from experimental runs. Effective translation can assist with both noise rejection and the construction of high-fidelity simulators. Building on recent work in diffusion probabilistic models, we present a novel framework for performing this mapping. We demonstrate the success of our approach in both synthetic domains and in data sourced from the Active-Target Time Projection Chamber.