EUVIMEDEUVIMED entdecken
Crossref

WorldGrow: Generating Infinite 3D World

Sikuang Li, Chen Yang, Jiemin Fang, Taoran Yi, Jia Lu, Jiazhong Cen, Lingxi Xie, Wei Shen, Qi Tian

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6433-6441

DOI: 10.1609/aaai.v40i8.37571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sikuang Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric and appearance inconsistencies across views, 3D implicit representations are hard to scale up, and current 3D foundation models are mostly object-centric, limiting their applicability to scene-level generation. Our key insight is leveraging strong generation priors from pre-trained 3D models for structured scene block generation. To this end, we propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis. Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting mechanism that enables context-aware scene extension; and (3) a coarse-to-fine generation strategy that ensures both global layout plausibility and local geometric/textural fidelity. Evaluated on the large-scale 3D-FRONT dataset, WorldGrow achieves SOTA performance in geometry reconstruction, while uniquely supporting infinite scene generation with photorealistic and structurally consistent outputs. These results highlight its capability for constructing large-scale virtual environments and potential for building future world models.

Zitieren

APA

Li, S., Yang, C., Fang, J., Yi, T., Lu, J., Cen, J., Xie, L., Shen, W., & Tian, Q. (2026). WorldGrow: Generating Infinite 3D World. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6433-6441. https://doi.org/10.1609/aaai.v40i8.37571

Vancouver

Li S, Yang C, Fang J, Yi T, Lu J, Cen J, et al. WorldGrow: Generating Infinite 3D World. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6433-6441. doi:10.1609/aaai.v40i8.37571

BibTeX
@article{Li2026,
  author = {Li, Sikuang and Yang, Chen and Fang, Jiemin and Yi, Taoran and Lu, Jia and Cen, Jiazhong and Xie, Lingxi and Shen, Wei and Tian, Qi},
  title = {WorldGrow: Generating Infinite 3D World},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {8},
  pages = {6433--6441},
  doi = {10.1609/aaai.v40i8.37571}
}
Kostenlos starten →