3D Field Data Reduction with Adaptive Sample-Based Gaussian-Encoded Reconstruction

The paper introduces a unified sample‑based Gaussian encoding method that represents structured grids, unstructured meshes, and particle data under a single fixed‑budget formulation. By initializing and refining Gaussian primitives directly from input samples while maintaining a prescribed primitive count, the method achieves higher reconstruction accuracy with fewer primitives—up to 4.8 dB higher PSNR and roughly a 44× reduction in primitive count compared to prior approaches. For time‑varying data, warm‑starting from the previous timestep further reduces optimization effort while preserving reconstruction quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.