跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-08AI 評分44

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

AI 導讀

OuroWorld 是一個無需遮罩的框架,可將靜態 3D Gaussian Splatting 場景轉化為可從不同視點觀看、動態循環的 3D 動態影像。在 39 個重建及生成場景上,OuroWorld 勝過所有基準方法,並在用戶研究比較中取得 70.8%-99.0% 的勝率。它可呈現一般形變、物件移動及光照變化,並以無需真值資料的評估方法衡量畫面生動度、自然度、循環接縫連貫性及場景質素。

正文

Published on Oct 8

Authors:

,

,

,

,

Abstract

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint. A vision-language model infers plausible dynamics and guides a video model to synthesize a reference video, which we lift and complete into multi-view videos. To learn from this imperfect supervision, we propose Inconsistency-Robust Periodic 4DGS: a Fourier-series deformation field guarantees looping by construction, while a Grounded Drift Field anchored at the reference view absorbs cross-view inconsistency. Unlike prior Eulerian methods limited to fluid-like motion, we capture general deformation, object motion, and illumination change. We introduce a ground-truth-free evaluation covering vividness, naturalness, loop seam coherence, and scene quality. On 39 reconstructed and generated scenes, OuroWorld outperforms all baselines and wins 70.8%-99.0% of user-study comparisons. Project page: https://ouroworld.userwei.com

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.12461

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.12461 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.12461 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.12461 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co