让雪落下！通过物理引导的分数蒸馏动画3D高斯场景的动态天气效果
Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation
AI总结：
本文提出物理引导的分数蒸馏框架，通过结合物理模拟和视频基于的分数蒸馏采样，实现3D场景的动态天气效果生成，提升真实感与动态一致性。
摘要：
3D高斯点划法最近实现了静态3D场景的快速且逼真重建。然而，对这类场景进行动态编辑仍是一个重大挑战。我们引入了物理引导的分数蒸馏框架，以解决一个根本矛盾：物理模拟提供了强大的运动先验，但不足以实现逼真效果，而基于视频的分数蒸馏采样（SDS）单独无法为复杂多粒子场景生成连贯的运动。我们通过统一的优化框架解决这一问题，其中物理模拟指导分数蒸馏共同优化运动先验以提高逼真度，同时优化外观。具体来说，我们学习了一个神经动力学模型，预测粒子运动和外观，通过结合视频SDS的损失函数和物理引导的先验进行端到端优化。这使我们能够实现逼真效果，同时确保动态合理。我们的框架能够生成全局动态天气效果，包括降雪、降雨、雾和沙尘暴，具有物理合理的运动。实验表明，我们的物理引导方法显著优于基线方法，消融实验确认联合优化对生成连贯、高保真的动态至关重要。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
