mlsanityData to 7 Oct 2026

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

arXiv 2610.12461 ↗First posted 8 Oct 2026cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 141 references that are in the map. First posted on arXiv 8 Oct 2026.

Builds on

31 of 141 references.

References · 31

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  3. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  4. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  5. 2018Demystifying MMD GANscited by 1,268
  6. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  7. 2025OpenAI GPT-5 System Cardcited by 910
  8. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  9. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  10. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  11. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  12. 2023Text-To-4D Dynamic Scene Generationcited by 204
19 more
  1. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 191
  2. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  3. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 150
  4. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 142
  5. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusioncited by 139
  6. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 91
  7. 2024Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusioncited by 76
  8. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 36
  9. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 34
  10. 2024VividDream: Generating 3D Scene with Ambient Dynamicscited by 21
  11. 2026VGGT-Omegacited by 20
  12. 2019Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesiscited by 15
  13. 2026AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstructioncited by 8
  14. 2026World Reconstruction From Inconsistent Viewscited by 8
  15. 2025Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Modelscited by 7
  16. 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusioncited by 4
  17. 2026DreamLoop: Controllable Cinemagraph Generation from a Single Photographcited by 2
  18. 2026AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animationcited by 1
  19. 2026Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embeddingcited by 1

Built on by

Not cited yet.