让3D场景重建动起来，添加自然的环境动态。
AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation
- 用时序变形场建模场景动态，结合预训练视频扩散模型迭代优化。
- 在5个大型室外场景上实现高质量新视角动画，保持静态结构完整。
- 适合需要沉浸式体验的3D场景重建与数字孪生应用。
大规模复杂重建场景的新视角渲染正变得越来越逼真，但多数重建仍为静态，缺乏使环境更具沉浸感的自然运动。我们提出AniGS，一种针对3D高斯溅射（3DGS）重建进行场景级动画的方法，可在保留刚性结构的同时添加细微、分布式的动态效果，如植被摆动。与仅限于物体中心或小区域的传统3D动画技术不同，AniGS专为大型、杂乱、可导航的场景设计。该方法以规范化的3DGS表示场景，并利用时序条件变形场建模运动。为实现全场景动画，我们借助预训练视频扩散模型，采用迭代数据-模型更新策略，逐步扩展视角覆盖范围，并通过渲染-精炼方案反复更新固定相机的训练视频。为防止静态区域出现意外运动，进一步引入组合式视频到视频精炼方案，将运动限制在目标区域。在五个真实世界的大规模户外场景上的实验表明，AniGS能够生成自然的环境动态和高质量的新视角视频，显著提升重建环境的沉浸式观感。
原文摘要 · Abstract (English)
Novel view rendering of large and complex reconstructed scenes is becoming increasingly photorealistic. However, most reconstructions remain static and lack the ambient motion that makes environments immersive. We present AniGS, a method for scene-level animation of 3D Gaussian Splatting (3DGS) reconstructions that adds subtle, distributed dynamics, e.g., vegetation motion, while preserving rigid structures. Unlike existing 3D animation techniques which are limited to object-centric subjects or small regions, AniGS is designed for large, cluttered, navigable scenes. AniGS represents the scene with a canonical 3DGS and models motion using a time-conditioned deformation field. To animate the entire scene, we leverage a pretrained video diffusion model and introduce an iterative dataset--model update strategy that progressively expands viewpoint coverage and repeatedly updates camera-fixed training videos using a render-and-refine scheme. To prevent artifacts from unintended motion in static areas, we further introduce a composed video-to-video refinement scheme that restricts motion to desired regions. Experiments on five real-world, large-scale outdoor scenes demonstrate that AniGS produces natural ambient dynamics and high-quality novel view videos, enabling more immersive viewing experiences of reconstructed environments.
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。