AI Insight
This work presents a method for compressing large-scale scientific simulation data by representing scalar fields as a fixed number of anisotropic Gaussian primitives. The approach analytically allocates Gaussians based on local field structure and refines them directly against the original data without changing primitive counts, achieving compression ratios from 2.2x to over 40,000x while maintaining 15.0-38.7 dB quality. The method can encode a billion-voxel volume using 1.4 million Gaussians in under four minutes on a single desktop GPU, with faster reduced-iteration variants completing in under one minute.
Why it matters
Scientific simulations increasingly generate data faster than storage and transfer capabilities allow, creating a bottleneck in computational research. This technique enables real-time compression during simulations with predictable computational budgets, and the encoded models retain scalar attributes that support post-processing visualization changes without re-encoding, making large-scale scientific data more accessible and manageable.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Scientific simulations often produce scalar volumes faster than they can be stored, transferred, and loaded, while in situ reduction must use only a limited share of simulation resources. This work encodes scalar fields as anisotropic Gaussian primitives under a fixed budget. The complete primitive set is allocated analytically from local field structure, including position, orientation, and shape, then refined directly against the scalar field without densification, pruning, or count changes. The selected budget determines encoded storage before refinement and, together with the iteration schedule, provides a controllable refinement-time budget. In a controlled benchmark, truncation-aware field evaluation reduces encoding time by up to 51x; 1.4 million Gaussians encode a billion-voxel volume in at most four minutes on one desktop GPU, with reduced-iteration refinement completing in under one minute. Across five datasets spanning 2.1 million to 1.1 billion evaluated voxels, compression-useful configurations achieve 15.0-38.7 dB PSNR at compression ratios from 2.2x to over 40,000x. Pre-encoding structure statistics characterize fields for which one-shot allocation yields limited gains from additional capacity. Because primitives retain scalar attributes rather than baked appearance, a single compact model serves every subsequent visualization state – supporting post-hoc transfer-function, colormap, lighting, and viewpoint changes without re-encoding.
Source: Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation