用物理粒子模拟未来3D运动，无需先验知识即可准确预测。
ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation
- 将场景拆解为静态属性与初始物理场，用神经微分方程建模连续运动。
- 在真实视频上实现高精度未来帧预测，渲染质量媲美顶尖重建方法。
- 适合需要物理一致性预测的场景，如机器人规划、虚拟仿真。
动态3D场景的未来外推能力是提升物理世界理解与预测建模的关键。现有动态3D重建方法虽能实现高质量的时间插值，但对未来预测常缺乏物理一致性。为此，本文提出ParticleGS，一种基于物理的框架，将动态3D场景重构为具有物理基础的系统。该框架包含三个核心组件：1）编码器将场景分解为静态属性与初始动态物理场；2）基于神经常微分方程（Neural ODEs）的演进器，学习连续时间下的运动规律以实现外推；3）解码器从演化后的粒子状态重建3D高斯表示用于渲染。通过此设计，ParticleGS将物理推理融入动态3D表征，实现准确且一致的未来预测。实验表明，ParticleGS在外推性能上达到当前最优水平，同时保持与领先动态3D重建方法相当的渲染质量。
原文摘要 · Abstract (English)
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 comparable to leading dynamic 3D reconstruction methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。