KnockGS：基于交互的物理高斯表示校准

中文摘要 AI 辅助

集成物理的三维高斯表示如今可让重建的可变形物体在明确的材料模型下进行模拟与渲染。然而，现有流程假设材料参数已知或手动指定，当需要从观测到的物体动力学推断这些参数时，其适用性受限。我们提出KnockGS，一种基于交互-响应的PhysicalGS框架，可在已知施加力的情况下，从三维高斯物体的动力学中估计其弹性与密度尺度。我们不再将物理模拟仅视为正向过程，而是将力诱导的响应转化为校准信号：从观测到的动力学中提取时间响应特征，再根据这些特征估计两种材料尺度，随后冻结该估计值并写回同一模拟器，使其可在未拟合过的交互中进行测试。我们在参数恢复和响应级保真度两方面评估该框架：将估计的尺度与隐藏的真实值对比，通过三维粒子轨迹、响应曲线统计量及渲染帧质量，测量重模拟物体与目标的契合度。在五个保留的材料目标上，我们的方法相比响应检索、全局回归或固定默认材料，能更准确地恢复尺度，且冻结后的估计值在方向和大小不同的交互下仍具预测性。因此，交互响应包含足够信息，可用于校准物理基三维高斯中的材料尺度。本研究是迈向交互式PhysicalGS系统的第一步，该系统可校准高斯资产，使其渲染外观与模拟响应保持一致。

英文摘要

Physics-integrated 3D Gaussian representations now allow reconstructed deformable objects to be simulated and rendered under explicit material models. Existing pipelines, however, assume that material parameters are known or manually specified, limiting their applicability when these parameters must be inferred from observed object dynamics. We propose KnockGS, an interaction-response PhysicalGS framework that estimates the elasticity and density scales of a 3D Gaussian object from its dynamics under a known applied force. Rather than treating physical simulation only as a forward process, we turn the force-induced response into a calibration signal: temporal response features are xtracted from the observed dynamics, the two material scales are estimated from those features, and the estimate is then frozen and written back into the same simulator so that it can be tested on an interaction it was never fitted to.We evaluate the framework on both parameter recovery and response-level fidelity. The estimated scales are compared against hidden ground truth, and the re-simulated object is measured against the target using 3D particle trajectories, response-curve statistics, and rendered-frame quality. Across five held-out material targets, our method recovers the scales substantially more accurately than response retrieval, global regression, or a fixed default material, and the frozen estimate remains predictive under interactions that differ in direction and in magnitude. Interaction response therefore carries enough information to calibrate material scales in physically grounded 3D Gaussian representations.Our study is a first step toward interactive PhysicalGS systems that calibrate a Gaussian asset whose rendered appearance and simulated response are consistent.

发表机构

• Tuojing Intelligence（拓境智能）
• Southeast University（东南大学）
• Stevens Institute of Technology（史蒂文斯理工学院）
• Tsinghua University（清华大学）
• Simple AI
• Imperial College London（伦敦帝国学院）
• Shanghai Jiao Tong University（上海交通大学）
• GigaAI（极佳科技）
• Sun Yat-sen University（中山大学）
• The University of Hong Kong（香港大学）

机构由 AI 辅助整理，请以论文原文为准。