More Like this

1. Particle Cloud Generation with Message Passing Generative Adversarial Networks

   Kansal, R.; Duarte, J.; Su, H.; Orzari, B.; Tomei, T.; Pierini, M.; Touranakou, M.; Vilmant, JR.; Gunopulos, D. (June 2021, ArXivorg)

   null (Ed.)

   In high energy physics (HEP), jets are collections of correlated particles produced ubiquitously in particle collisions such as those at the CERN Large Hadron Collider (LHC). Machine-learning-based generative models, such as generative adversarial networks (GANs), have the potential to significantly accelerate LHC jet simulations. However, despite jets having a natural representation as a set of particles in momentum-space, a.k.a. a particle cloud, to our knowledge there exist no generative models applied to such a dataset. We introduce a new particle cloud dataset (JetNet), and, due to similarities between particle and point clouds, apply to it existing point cloud GANs. Results are evaluated using (1) the 1-Wasserstein distance between high- and low-level feature distributions, (2) a newly developed Fréchet ParticleNet Distance, and (3) the coverage and (4) minimum matching distance metrics. Existing GANs are found to be inadequate for physics applications, hence we develop a new message passing GAN (MPGAN), which outperforms existing point cloud GANs on virtually every metric and shows promise for use in HEP. We propose JetNet as a novel point-cloud-style dataset for the machine learning community to experiment with, and set MPGAN as a benchmark to improve upon for future generative models. 

   more » « less
2. A PARALLEL ALGORITHM FOR LOCAL POINT DENSITY INDEX COMPUTATION OF LARGE POINT CLOUDS

   https://doi.org/10.5194/isprs-annals-VIII-4-W2-2021-75-2021  

   Vo, A. V.; Lokugam Hewage, C. N.; Le Khac, N. A.; Bertolotto, M.; Laefer, D. (January 2021, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences)

   Abstract. Point density is an important property that dictates the usability of a point cloud data set. This paper introduces an efficient, scalable, parallel algorithm for computing the local point density index, a sophisticated point cloud density metric. Computing the local point density index is non-trivial, because this computation involves a neighbour search that is required for each, individual point in the potentially large, input point cloud. Most existing algorithms and software are incapable of computing point density at scale. Therefore, the algorithm introduced in this paper aims to address both the needed computational efficiency and scalability for considering this factor in large, modern point clouds such as those collected in national or regional scans. The proposed algorithm is composed of two stages. In stage 1, a point-level, parallel processing step is performed to partition an unstructured input point cloud into partially overlapping, buffered tiles. A buffer is provided around each tile so that the data partitioning does not introduce spatial discontinuity into the final results. In stage 2, the buffered tiles are distributed to different processors for computing the local point density index in parallel. That tile-level parallel processing step is performed using a conventional algorithm with an R-tree data structure. While straight-forward, the proposed algorithm is efficient and particularly suitable for processing large point clouds. Experiments conducted using a 1.4 billion point data set acquired over part of Dublin, Ireland demonstrated an efficiency factor of up to 14.8/16. More specifically, the computational time was reduced by 14.8 times when the number of processes (i.e. executors) increased by 16 times. Computing the local point density index for the 1.4 billion point data set took just over 5 minutes with 16 executors and 8 cores per executor. The reduction in computational time was nearly 70 times compared to the 6 hours required without parallelism. 

   more » « less
3. RGB2Point: 3D Point Cloud Generation from Single RGB Images

   https://doi.org/10.1109/WACV61041.2025.00292  

   Lee, Jae Joong; Benes, Bedrich (February 2025, IEEE)

   We introduce RGB2Point, an unposed single-view RGB image to a 3D point cloud generation based on Transformer. RGB2Point takes an input image of an object and generates a dense 3D point cloud. Contrary to prior works based on CNN layers and diffusion-denoising approaches, we use pre-trained Transformer layers that are fast and generate high-quality point clouds with consistent quality over available categories. Our generated point clouds demonstrate high quality on a real-world dataset, as evidenced by improved Chamfer distance (51.15%) and Earth Mover’s distance (36.17%) metrics compared to the current state-of the-art. Additionally, our approach shows a better quality on a synthetic dataset, achieving better Chamfer distance (39.26%), Earth Mover’s distance (26.95%), and F-score (47.16%). Moreover, our method produces 63.1% more consistent high-quality results across various object categories compared to prior works. Furthermore, RGB2Point is computationally efficient, requiring only 2.3GB of VRAM to reconstruct a 3D point cloud from a single RGB image, and our implementation generates the results 15,133× faster than a SOTA diffusion-based model. 

   more » « less
4. EPiC-GAN: Equivariant point cloud generation for particle jets

   https://doi.org/10.21468/SciPostPhys.15.4.130  

   Buhmann, Erik; Kasieczka, Gregor; Thaler, Jesse (January 2023, SciPost Physics)

   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. 

   more » « less
5. Microphysical processes producing high ice water contents (HIWCs) in tropical convective clouds during the HAIC-HIWC field campaign: evaluation of simulations using bulk microphysical schemes

   https://doi.org/10.5194/acp-21-6919-2021  

   Huang, Yongjie; Wu, Wei; McFarquhar, Greg M.; Wang, Xuguang; Morrison, Hugh; Ryzhkov, Alexander; Hu, Yachao; Wolde, Mengistu; Nguyen, Cuong; Schwarzenboeck, Alfons; et al (January 2021, Atmospheric Chemistry and Physics)

   Abstract. Regions with high ice water content (HIWC), composed of mainly small ice crystals, frequently occur over convective clouds in the tropics. Such regions can have median mass diameters (MMDs) <300 µm and equivalent radar reflectivities <20 dBZ. To explore formation mechanisms for these HIWCs, high-resolution simulations of tropical convective clouds observed on 26 May 2015 during the High Altitude Ice Crystals – High Ice Water Content (HAIC-HIWC) international field campaign based out of Cayenne, French Guiana, are conducted using the Weather Research and Forecasting (WRF) model with four different bulk microphysics schemes: the WRF single‐moment 6‐class microphysics scheme (WSM6), the Morrison scheme, and the Predicted Particle Properties (P3) scheme with one- and two-ice options. The simulations are evaluated against data from airborne radar and multiple cloud microphysics probes installed on the French Falcon 20 and Canadian National Research Council (NRC) Convair 580 sampling clouds at different heights. WRF simulations with different microphysics schemes generally reproduce the vertical profiles of temperature, dew-point temperature, and winds during this event compared with radiosonde data, and the coverage and evolution of this tropical convective system compared to satellite retrievals. All of the simulations overestimate the intensity and spatial extent of radar reflectivity by over 30 % above the melting layer compared to the airborne X-band radar reflectivity data. They also miss the peak of the observed ice number distribution function for 0.1<1 mm. Even though the P3 scheme has a very different approach representing ice, it does not produce greatly different total condensed water content or better comparison to other observations in this tropical convective system. Mixed-phase microphysical processes at −10 ∘C are associated with the overprediction of liquid water content in the simulations with the Morrison and P3 schemes. The ice water content at −10 ∘C increases mainly due to the collection of liquid water by ice particles, which does not increase ice particle number but increases the mass/size of ice particles and contributes to greater simulated radar reflectivity. 

   more » « less