AI 中文总结
PhysReal提出视频驱动的混合本构建模框架，集成解析专家模型与神经残差及MPM模拟器，通过渐进课程从稀疏观察学习真实可变形物体物理，在动态重建和预测上表现优越。
AI 中文摘要
从视觉观察中学习物理上合理的动力学对于交互式世界模型和具身智能体至关重要。然而，建模真实世界的可变形物体仍然具有挑战性，因为其动力学通常源于复杂的、空间异质的材料响应。为了解决这一挑战，我们提出了PhysReal，一个视频驱动的框架，用于学习和模拟真实可变形物体的底层物理。PhysReal集成了一个空间变化的混合专家-神经本构模型与可微分的MPM模拟器和3DGS渲染器。解析专家模型提供了可解释的物理先验，而神经本构残差则捕捉超出预定义公式的材料响应。空间分布的补丁参数化本构场，实现了局部材料变化的连续表示。为了从稀疏的视觉观察中组织该模型的识别，我们采用了一个渐进式课程，依次优化全局材料属性、空间变化的局部参数和神经本构残差，并辅以互补的运动和掩码监督。在多样化的可变形物体交互上的大量实验表明，PhysReal在动态重建和未来状态预测方面实现了优越的性能，同时显示出对下游机器人应用的强大潜力。
英文摘要
Learning physically plausible dynamics from visual observations is essential for interactive world models and embodied agents. However, modeling real-world deformable objects remains challenging because their dynamics often arise from complex, spatially heterogeneous material responses. To address this challenge, we propose PhysReal, a video-driven framework for learning and simulating the underlying physics of real deformable objects. PhysReal integrates a spatially varying hybrid expert-neural constitutive model with a differentiable MPM simulator and 3DGS renderer. Analytical expert models provide interpretable physical priors, while neural constitutive residuals capture material responses beyond predefined formulations. Spatially distributed patches parameterize the constitutive field, enabling a continuous representation of local material variations. To organize the identification of this model from sparse visual observations, we adopt a progressive curriculum that sequentially optimizes global material properties, spatially varying local parameters, and neural constitutive residuals, together with complementary motion and mask supervision. Extensive experiments on diverse deformable-object interactions demonstrate that PhysReal achieves superior performance in dynamic reconstruction and future-state prediction, while showing strong potential for downstream robotic applications.
CommentsProject website: https://physreal.github.io/anonymous_web
