3D Gaussian Splatting has recently enabled fast and photorealistic reconstruction of static 3D scenes. However, dynamic editing of such scenes remains a significant challenge. We introduce a novel framework, Physics-Guided Score Distillation, to address a fundamental conflict: physics simulation provides a strong motion prior that is insufficient for photorealism , while video-based Score Distillation Sampling (SDS) alone cannot generate coherent motion for complex, multi-particle scenarios. We resolve this through a unified optimization framework where physics simulation guides Score Distillation to jointly refine the motion prior for photorealism while simultaneously optimizing appearance. Specifically, we learn a neural dynamics model that predicts particle motion and appearance, optimized end-to-end via a combined loss integrating Video-SDS for photorealism with our physics-guidance prior. This allows for photorealistic refinements while ensuring the dynamics remain plausible. Our framework enables scene-wide dynamic weather effects, including snowfall, rainfall, fog, and sandstorms, with physically plausible motion. Experiments demonstrate our physics-guided approach significantly outperforms baselines, with ablations confirming this joint refinement is essential for generating coherent, high-fidelity dynamics.

翻译：三维高斯溅射技术最近实现了静态三维场景的快速且逼真的重建。然而，对此类场景进行动态编辑仍然是一个重大挑战。我们引入了一个新颖的框架——物理引导的分数蒸馏，以解决一个根本性的冲突：物理模拟提供了强大的运动先验，但其本身不足以实现照片级真实感；而仅基于视频的分数蒸馏采样又无法为复杂的多粒子场景生成连贯的运动。我们通过一个统一的优化框架解决了这一问题，在该框架中，物理模拟引导分数蒸馏，共同为追求真实感而优化运动先验，同时优化外观。具体而言，我们学习一个预测粒子运动和外观的神经动力学模型，通过一个结合了用于真实感的视频分数蒸馏损失和我们提出的物理引导先验的混合损失，进行端到端优化。这使得在确保动力学过程保持合理性的同时，能够进行逼真的细节优化。我们的框架能够实现场景级的动态天气效果，包括降雪、降雨、雾和沙尘暴，并具有物理上合理的运动。实验表明，我们这种物理引导的方法显著优于基线模型，消融研究也证实了这种联合优化对于生成连贯、高保真的动态效果至关重要。