AI 中文总结
NewtonGS是用于高斯场景动画的物理结构对象级神经牛顿动力学框架，用22维状态表示对象，结合解析动力学与学习残差，在State-32和Gaussian-32数据集上优于基线，实现状态到动画高斯对象的有效转换。
AI 中文摘要
在静态3D高斯场景中对物体进行动画化需要显式的对象级动态状态和可控的物体运动模型。现有的动态高斯方法主要用于重建时变场景或模拟变形，而非提供可直接控制的紧凑对象状态。为解决这一缺口，本文提出NewtonGS，一种用于对象级状态展开和高斯场景动画的物理结构框架。NewtonGS用22维状态表示每个对象，涵盖位姿、线速度与角速度、各向异性尺度及其变化率、质量和接触属性。其高斯神经牛顿动力学（Gaussian-NND）模型结合了解析平移、四元数运动学、重力、阻尼和尺度恢复动力学，以及学习到的连续和接触残差。离散事件图处理地面接触。预测的位姿和尺度定义共享仿射变换，用于更新与每个对象关联的所有高斯的均值和协方差。我们构建了两个程序生成的数据集：用于状态展开评估的State-32和用于状态到高斯变换的Gaussian-32。在State-32的分布内和速度范围偏移划分上，NewtonGS的轨迹RMSE、最终位移误差和速度RMSE均低于5种解析基线。对Gaussian-32的实验进一步证明了从预测状态到动画高斯对象的有效转换。
英文摘要
Animating objects in a static 3D Gaussian scene requires an explicit object-level dynamic state and a controllable model of object motion. Existing dynamic Gaussian methods primarily reconstruct time-varying scenes or simulate deformation, rather than provide compact object states for direct control. To address this gap, we present NewtonGS, a physics-structured framework for object-level state rollout and Gaussian scene animation. NewtonGS represents each object with a 22-dimensional state covering pose, linear and angular velocity, anisotropic scale and its rate, mass, and contact properties. Its Gaussian Neural Newtonian Dynamics (Gaussian-NND) model combines analytic translation, quaternion kinematics, gravity, damping, and scale-restoration dynamics with learned continuous and contact residuals. A discrete event map handles floor contact. Predicted poses and scales define a shared affine transformation that updates the means and covariances of all Gaussians associated with each object. We construct two procedurally generated datasets: State-32 for state-rollout evaluation and Gaussian-32 for state-to-Gaussian transformation. On both the in-distribution and velocity-range-shift splits of State-32, NewtonGS achieves lower trajectory RMSE, final displacement error, and velocity RMSE than five analytic baselines. Experiments on Gaussian-32 further demonstrate effective conversion from predicted states to animated Gaussian objects.
Comments40 pages, 15 figures
