发表机构
University of California, Davis; Argonne National Laboratory（加利福尼亚大学戴维斯分校; 阿贡国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出固定预算下结构感知分配的高斯体积编码方法，可快速编码标量体积，在多数据集上实现高压缩率与PSNR，支持可视化属性事后调整。
AI 中文摘要
科学模拟生成标量体积的速度往往快于其存储、传输和加载的速度，而原位缩减必须仅使用模拟资源的有限份额。本研究将标量场编码为固定预算下的各向异性高斯基元，完整的基元集根据局部场结构（包括位置、方向和形状）进行解析分配，随后直接对标量场进行优化，无需加密、剪枝或改变数量。选定的预算决定了优化前的编码存储量，结合迭代调度可提供可控的优化时间预算。在受控基准测试中，感知截断的场评估将编码时间最多减少51倍；140万个高斯基元在单台桌面GPU上最多4分钟即可编码10亿体素的体积，缩减迭代次数的优化可在1分钟内完成。在覆盖210万至11亿个评估体素的5个数据集上，压缩有用配置在2.2倍至超过40000倍的压缩率下实现15.0-38.7 dB的PSNR。预编码结构统计量表征了一次性分配从额外容量中获益有限的场。由于基元保留标量属性而非烘焙外观，单个紧凑模型可适用于所有后续可视化状态，支持事后传递函数、颜色映射、光照和视点变化，无需重新编码。
英文摘要
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.
Comments10 pages, 6 figures, 6 tables
