用物理引导生成雪雨等天气效果，让3D场景动起来又逼真。
Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation
- 结合物理模拟与图像生成，统一优化运动与外观。
- 在真实场景中实现雪、雨、沙尘等动态天气，效果逼真且运动合理。
- 适合做影视级3D动态场景生成的研究者或从业者。
3D Gaussian Splatting 近期实现了静态3D场景的快速、逼真重建，但动态编辑仍具挑战。本文提出一种新框架——物理引导得分蒸馏（Physics-Guided Score Distillation），解决核心矛盾：物理模拟提供强运动先验但缺乏逼真感，而视频得分蒸馏采样（Video-SDS）无法生成复杂多粒子场景的连贯运动。通过统一优化框架，让物理模拟引导得分蒸馏，在提升视觉逼真度的同时同步优化运动合理性。具体地，学习一个神经动力学模型以预测粒子运动与外观，通过融合视频SDS损失与物理引导先验的联合损失端到端优化。该方法可实现全局动态天气效果，包括雪、雨、雾、沙暴等，且运动符合物理规律。实验表明，本方法显著优于基线，消融实验证明联合优化对生成连贯高保真动态至关重要。
原文摘要 · Abstract (English)
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.
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。