PhysHO：从单目视频重建基于物理的动态 3D 高斯人体与物体
PhysHO: Physics-Based Dynamic 3D Gaussian Human and Object from Monocular Video
将 LBS 作为可解释的驱动先验、用 MPM 传播接触力，并用逐粒子的残差神经本构模型刻画非均质材料，为单目视频中人体-物体交互的物理可信重建与未来运动预测提供了可复用的建模范式。
原文依据 tightly couples SMPL-driven Linear Blend Skinning (LBS) with a Material Point Method (MPM) simulator
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单段视频中对人体-物体动力学进行物理可信的重建，在基于物理的方法中仍鲜有探索。多数已有方法忽略了人体产生的内部驱动，假设运动仅由重力和简单接触驱动。它们还依赖理想化的本构定律，对异质且各向异性的材料拟合不足。我们提出 PhysHO，将 SMPL 驱动的线性混合蒙皮（LBS）与物质点法（MPM）模拟器紧密耦合，以弥补上述不足。我们的关键洞见是将 LBS 用作可解释的驱动先验，并用 MPM 在物理约束下通过接触传播这些力。具体而言，我们借助由 LBS 轨迹引导的 PD 控制器推导出有针对性的驱动，并通过可学习的 LBS 影响因子对每个粒子进行门控，使只有位于 SMPL 体积内的粒子被直接驱动。我们在专家弹性-塑性模型之上叠加残差神经本构定律，并以逐粒子为条件来建模真实材料，从而刻画异质性与各向异性。我们通过保持结构的三维流监督以及渐进式、损失平衡的训练调度来稳定单目学习。PhysHO 以高保真度重建观测到的动力学，并能预测未来运动，以及在新的人体动作下模拟结果。实验结果表明，该方法能够稳健地处理超越纯重力场景的人体驱动交互。
英文原文摘要 1412 字符
Physically plausible reconstruction of human-object dynamics from a single video remains under-explored in physics-based methods. Most prior approaches omit human-generated internal actuation by assuming motion driven solely by gravity and simple contacts. They also rely on idealized constitutive laws that underfit heterogeneous and anisotropic materials. We introduce PhysHO, which tightly couples SMPL-driven Linear Blend Skinning (LBS) with a Material Point Method (MPM) simulator to address these gaps. Our key insight is to use LBS as an interpretable actuation prior and MPM to propagate those forces through contact under physical constraints. Concretely, we derive targeted actuation with a PD controller guided by LBS trajectories and gate it per particle via a learnable LBS-impact factor so that only particles inside the SMPL volume are directly actuated. We model real materials with residual neural constitutive laws layered on expert elastic-plastic models and conditioned on per particle to capture heterogeneity and anisotropy. We stabilize monocular learning with structure-preserving 3D flow supervision and a progressive and loss-balanced training schedule. Our PhysHO reconstructs observed dynamics with high fidelity, and predicts future motion and simulates outcomes under novel human actions. Experimental results demonstrate robust human-driven interactions beyond gravity-only scenes.