cs.CVNov 10, 2026

Neural Compression for Scientific Particle Data: Perspectives on How Learning Can Help

Authors: Tian Qiu, Carolina Cuesta-Lazaro, Sheng Di, Haewon Jeong

Organizations: University of California, Santa Barbara · New York University · Flatiron Institute · Argonne National Laboratory

Abstract

As particle-based simulations grow in scale, efficient compression of scientific data becomes critical. Neural point cloud compression (PCC) methods excel on computer vision (CV) benchmarks, but do they transfer to scientific particle data? We highlight that scientific particles differ from CV point clouds in fractal dimension: CV point clouds are locally planar, but particles are not. This key difference limits the effectiveness of the octree data structure that underpins most PCC methods. Neural codecs achieve only marginal bitrate reductions over the traditional G-PCC baseline on scientific data, revealing a significant performance gap. Supported by an evaluation spanning domains of cosmology, molecular dynamics, and plasma physics, we outline where the structure of scientific data limits current neural approaches and where learning can help in the future.

Figures & tables

Explore similar work

CardsList
  1. Preserving Clusters in Error-Bounded Lossy Compression of Particle Data

    Apr 20, 2026Congrong Ren, Sheng Di, Katrin Heitmann +2Clustering

  2. Geometry-Based Compression of Plenoptic Point Clouds

    Aug 11, 2026Davi R. Freitas, Gustavo L. Sandri, Ricardo L. de QueirozPoint Cloud Compression

  3. Neural Particle Automata: Learning Self-Organizing Particle Dynamics

    Jan 22, 2026Hyunsoo Kim, Ehsan Pajouheshgar, Sabine Süsstrunk +2Neural Cellular AutomataDynamical Systems