OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs· OuroWorld：将3D世界变为动态影画
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
将3D世界转换为多样且无限循环的动态影画。
- 核心方法
- 利用一个免掩膜框架，结合视觉-语言模型推断合理动态，并引导视频模型合成人参考视频，再将其转换为多视角视频。提出了一个从这种不完美监督中学习的方法Inconsistency-Robust Periodic 4DGS，使用傅里叶级数变形场保证循环，并通过参考视图锚定的Grounded Drift Field吸收跨视角不一致性。
- 适合谁读
- 研究者 / 工程师 / 产品
- 要解决的问题
- 现有的3D世界模型生成的场景虽然逼真可探索，但时间上静止不动。
- 关键实验
- 在39个重建和生成的场景上进行了实验，OuroWorld在所有基线上表现最佳，在用户研究中赢得70.8%-99.0%的比较。
- 主要贡献
- 能够捕捉一般变形、物体运动和光照变化，不受限于流体运动，提供一个无地面实况的评估标准。
- 意义与局限
- 突破了传统3D动态场景生成的局限，提升了多样性和自然度，但可能存在模型泛化能力的限制。