GaussianBench:面向高斯场景表示的物理保真度评测
GaussianBench: Physics-Fidelity Evaluation for Gaussian Scene Representations
Chukwudalu Dumebi-Kachikwu
中文摘要
3D Gaussian Splatting 已从静态重建演进为集成物理化的表示,旨在预测场景在交互作用下的变化。这带来一个评估难题:一次推演可能看起来合理,却基于错误的内部力学机制;与观测运动在视觉上一致,并不能说明模型对新外力、材料修改、接触或热干预给出了正确响应。本文提出 GaussianBench,一套面向物理集成高斯场景表示的物理保真度评测套件。它采用基于文件的冻结场景、与仿真器无关的打分器,以及解析或实测参考。该基准测试守恒律、连续介质响应、异质材料耦合、高斯协方差传输与渲染、相变热行为以及反事实响应。每个参考都声明其适用范围,结果区分 PASS、FAIL、NA、INVALID,将物理失败、未支持能力与无效比较分开。本文同时给出 GaussianFlesh,一种热力学参考参赛方案:持久的 3D 高斯同时作为渲染基元和连续介质物质点,由共享网格 MPM 求解器推进,具备逐粒子本构派发以及持久的热与相态。评测涵盖六个已发布的外部系统:PhysGaussian、GaussianFluent、OmniPhysGS、PhysDreamer、Physics3D 与 GASP。以相同方式测试每个系统,暴露出它们原始评测遗漏的失败:某个系统可正确模拟单一材料,却在两种材料交界处失效;或对从未产生的形变正确地更新其高斯。匹配缺陷与容差审计证实这些区别源自测试设计本身。物理集成高斯系统必须基于其内部物理状态而非仅仅推演的视觉合理性进行测试。
关键要点
- 01指出现有 3D Gaussian Splatting 物理集成系统的评估盲区:视觉可信并不等价于内部物理机制正确
- 02提出 GaussianBench 评测套件,采用冻结文件场景、与仿真器无关的打分器以及解析/实测参考,覆盖守恒、连续介质、异质材料耦合、协方差传输、相变与反事实响应
- 03同时发布 GaussianFlesh 参考方案,使用 MPM 求解器与逐粒子本构派发,高斯兼具渲染基元与连续介质物质点双重角色
- 04统一测试 PhysGaussian、GaussianFluent、OmniPhysGS、PhysDreamer、Physics3D、GASP 六个系统,发现其在多材料界面、协方差更新等方面的失败未被原评测捕获
- 05强调应针对内部物理状态而非视觉合理性进行测试,区分 PASS、FAIL、NA、INVALID 四类结果
解读
尚无解读。
原始英文摘要
arXiv:2610.10554v1 Announce Type: cross Abstract: 3D Gaussian Splatting has evolved from static reconstruction toward physics-integrated representations meant to predict how scenes change under interaction. This creates an evaluation problem: a rollout can look plausible while relying on incorrect internal mechanics, and visual agreement with observed motion does not establish a correct response to a new force, material edit, contact, or thermal intervention. We introduce GaussianBench, a physics-fidelity evaluation suite for physics-integrated Gaussian scene representations. It uses frozen file-based scenes, simulator-independent scorers, and analytical or measured references. The benchmark tests conservation, continuum response, heterogeneous-material coupling, Gaussian covariance transport and rendering, thermal phase change, and counterfactual response. Each reference declares its regime of validity, and outcomes distinguish PASS, FAIL, NA, and INVALID, separating physical failures from unsupported capabilities and invalid comparisons. We also provide GaussianFlesh, a thermomechanical reference entrant in which persistent 3D Gaussians act as both rendering primitives and continuum material points, advanced by a shared-grid MPM solver with per-particle constitutive dispatch and persistent thermal and phase state. We evaluate six released external systems: PhysGaussian, GaussianFluent, OmniPhysGS, PhysDreamer, Physics3D, and GASP. Testing every system the same way reveals failures that their original evaluations missed: a system can simulate a single material correctly but fail where two materials meet, or update its Gaussians correctly for a deformation it never produced. Matched faults and tolerance audits confirm these distinctions arise from the intended tests. Physics-integrated Gaussian systems must therefore be tested on their internal physical state, not just on whether their rollouts look plausible.