PhysGS：用于物理属性估计的贝叶斯推断高斯泼溅
PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation
把 3D 高斯泼溅从几何/外观重建扩展为可微的贝叶斯后验推断框架，每个高斯点携带材质与物理属性信念并随观测迭代更新，同时区分偶然与认知不确定性；做机器人操作、仿真到现实或需要从视觉推断物体物理量的工作可直接复用这一「高斯点 + 概率信念」的表示。
原文依据 We formulate property estimation as Bayesian inference over Gaussian splats, where material and property beliefs are iteratively refined as new observations arrive.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论理解摩擦、刚度、硬度与材质构成等物理属性，是使机器人能够安全、有效地与周围环境交互的关键。然而，现有的三维重建方法聚焦于几何与外观，无法推断这些底层物理属性。本文提出 PhysGS，它是三维高斯泼溅的贝叶斯推断扩展，可从视觉线索与视觉—语言先验中估计稠密的逐点物理属性。我们将属性估计建模为高斯泼溅上的贝叶斯推断，其中材质与属性信念随着新观测的到来而被迭代细化。PhysGS 还对偶然不确定性与认知不确定性进行建模，从而支持不确定性感知的物体与场景解读。在物体尺度数据集（ABO-500）、室内与室外真实世界数据集上，与确定性基线相比，PhysGS 将质量估计的精度最多提升 22.8%，将邵氏硬度误差最多降低 61.2%，并将动摩擦误差最多降低 18.1%。结果表明，PhysGS 在单一且空间连续的框架中统一了三维重建、不确定性建模与物理推理，用于稠密物理属性估计。
英文原文摘要 1236 字符
Understanding physical properties such as friction, stiffness, hardness, and material composition is essential for enabling robots to interact safely and effectively with their surroundings. However, existing 3D reconstruction methods focus on geometry and appearance and cannot infer these underlying physical properties. We present PhysGS, a Bayesian-inferred extension of 3D Gaussian Splatting that estimates dense, per-point physical properties from visual cues and vision--language priors. We formulate property estimation as Bayesian inference over Gaussian splats, where material and property beliefs are iteratively refined as new observations arrive. PhysGS also models aleatoric and epistemic uncertainties, enabling uncertainty-aware object and scene interpretation. Across object-scale (ABO-500), indoor, and outdoor real-world datasets, PhysGS improves accuracy of the mass estimation by up to 22.8%, reduces Shore hardness error by up to 61.2%, and lowers kinetic friction error by up to 18.1% compared to deterministic baselines. Our results demonstrate that PhysGS unifies 3D reconstruction, uncertainty modeling, and physical reasoning in a single, spatially continuous framework for dense physical property estimation.