ParticleGS：从视频学习神经高斯粒子动力学以实现无先验物理运动外推
ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation
将动态3D场景表示为物理粒子系统，用Neural ODE学习连续时间动力学，实现无先验的未来运动外推；其编码器-演化器-解码器架构可复用于其他需要物理一致性的动态重建任务。
原文依据 an evolver based on Neural Ordinary Differential Equations (Neural ODEs) that learns continuous-time dynamics for motion extrapolation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论将动态3D场景外推到观测时间范围之外的能力是推进物理世界理解和预测建模的基础。现有的动态3D重建方法在时序插值方面已实现高保真渲染，但在预测未来时通常缺乏物理一致性。为解决这一问题，我们提出ParticleGS，一个基于物理的框架，将动态3D场景重新表述为具有物理基础的系统。ParticleGS包含三个关键组件：1）一个编码器，将场景分解为静态属性和初始动态物理场；2）一个基于神经常微分方程（Neural ODEs）的演化器，学习连续时间动力学以进行运动外推；3）一个解码器，从演化后的粒子状态重建3D高斯以进行渲染。通过这一设计，ParticleGS将物理推理集成到动态3D表示中，能够准确且一致地预测未来。实验表明，ParticleGS在外推方面达到了最优性能，同时保持了渲染质量。
英文原文摘要 1124 字符
The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D reconstruction methods have achieved high-fidelity rendering of temporal interpolation, but typically lack physical consistency in predicting the future. To overcome this issue, we propose ParticleGS, a physics-based framework that reformulates dynamic 3D scenes as physically grounded systems. ParticleGS comprises three key components: 1) an encoder that decomposes the scene into static properties and initial dynamic physical fields; 2) an evolver based on Neural Ordinary Differential Equations (Neural ODEs) that learns continuous-time dynamics for motion extrapolation; and 3) a decoder that reconstructs 3D Gaussians from evolved particle states for rendering. Through this design, ParticleGS integrates physical reasoning into dynamic 3D representations, enabling accurate and consistent prediction of the future. Experiments show that ParticleGS achieves state-of-the-art performance in extrapolation while maintaining rendering quality.