{"slug": "anigs-bridging-rendering-and-diffusion-prior-for-3d-scene-animation", "title": "AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation", "summary": "Researchers present AniGS, a method for scene-level animation of 3D Gaussian Splatting reconstructions that adds subtle, distributed dynamics like vegetation motion while preserving rigid structures, using a time-conditioned deformation field and a pretrained video diffusion model. 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.", "body_md": "arXiv:2607.18539v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/anigs-bridging-rendering-and-diffusion-prior-for-3d-scene-animation", "canonical_source": "https://arxiv.org/abs/2607.18539", "published_at": "2026-07-22 04:00:00+00:00", "updated_at": "2026-07-22 04:13:48.448150+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "generative-ai"], "entities": ["AniGS", "3D Gaussian Splatting", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/anigs-bridging-rendering-and-diffusion-prior-for-3d-scene-animation", "markdown": "https://wpnews.pro/news/anigs-bridging-rendering-and-diffusion-prior-for-3d-scene-animation.md", "text": "https://wpnews.pro/news/anigs-bridging-rendering-and-diffusion-prior-for-3d-scene-animation.txt", "jsonld": "https://wpnews.pro/news/anigs-bridging-rendering-and-diffusion-prior-for-3d-scene-animation.jsonld"}}