Authors: Bo Jiang, Youyuan Liu, and Taolue Yang (Temple University); Sheng Di (Argonne National Laboratory); and Sian Jin (Temple University)
Abstract: Large-scale particle simulations produce hundreds of millions of particles, straining storage, transfer, and interactive visualization. Existing lossy compressors such as SZ3 operate in data space and provide no guarantees on downstream visualization fidelity. We propose ParticleGS, a visualization-aware framework based on 3D Gaussian Splatting (3DGS) that learns a compact representation directly optimized for rendered image quality, combining (1) a multi-stage, multi-orbit training pipeline, (2) VizMapper, a lightweight network that adapts a single trained model to user-specified visualization parameters at inference time, and (3) spatial block training with KD-tree decomposition and global fine-tuning. On a 281-million-particle HACC cosmological simulation, our eight-block model reaches 30.03 dB PSNR at 65× compression, outperforming SZ3 by 5–8 dB at comparable ratios, and generalizes without tuning to additional HACC regions and a dark-matter-only FIRE-2 simulation. It renders at 662 FPS on a single GPU, over 2,300× faster than ParaView on the full particle data.
Presentation: file