发表机构
University of Illinois Urbana-Champaign; Waymo; Carnegie Mellon University; Meta（伊利诺伊大学厄巴纳-香槟分校; Waymo公司; 卡内基梅隆大学; Meta）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AniGS旨在为3DGS重建的大型场景添加动画，用规范3DGS表示场景，借时间条件变形场建模运动，利用预训练视频扩散模型及迭代更新策略，防止静态区域运动伪影，实验证明该方法能产生自然动态和高质量新视图视频。
AI 中文摘要
大型复杂重建场景的新视图渲染越来越逼真。然而，大多数重建仍为静态，缺乏使环境身临其境的环境运动。我们提出AniGS，一种用于3D高斯点渲染（3DGS）重建的场景级动画方法，它能在保留刚性结构的同时添加微妙的分布式动态，如植被运动。与现有局限于以对象为中心的主题或小区域的3D动画技术不同，AniGS专为大型、杂乱、可导航场景设计。它用规范的3DGS表示场景，并用时间条件变形场对运动建模。为使整个场景动起来，利用预训练视频扩散模型并引入迭代数据集-模型更新策略，逐步扩大视点覆盖范围，并使用渲染和细化方案反复更新相机固定训练视频。为防止静态区域意外运动产生伪影，还引入组合视频到视频的细化方案，将运动限制在期望区域。在五个真实世界的大型户外场景上的实验表明，AniGS能产生自然的环境动态和高质量的新视图视频，实现对重建环境更身临其境的观看体验。
英文摘要
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.
CommentsPreprint. Project page: https://yccyenchicheng.github.io/AniGS/
