Metraipolis › archive › dc_cfdf45fa82ad

WorldClaw: Agentic 3D Open-World Generation at Scale — arXiv:2608.05248

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.05248
License (as archived): CC0-1.0
Archived: 2026-10-31T10:37:51.632Z
SHA-256 of the archived text: 08a74c1c1551c00614c2c4a3f2d69b34673051386d685d5bf8f01587de3e109a
Stable URL of this page: https://metraipolis.com/documento/dc_cfdf45fa82ad

How to cite

WorldClaw: Agentic 3D Open-World Generation at Scale — arXiv:2608.05248 — arXiv (en), https://arxiv.org/abs/2608.05248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cfdf45fa82ad (Metraipolis archive dc_cfdf45fa82ad, sha256 08a74c1c1551c00614c2c4a3f2d69b34673051386d685d5bf8f01587de3e109a)

BibTeX

@misc{dccfdf45fa82ad,
  title = {WorldClaw: Agentic 3D Open-World Generation at Scale — arXiv:2608.05248},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05248},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cfdf45fa82ad; sha256 08a74c1c1551c00614c2c4a3f2d69b34673051386d685d5bf8f01587de3e109a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, and explicit assets suitable for downstream editing and reuse. We present WorldClaw, a fully agentic, coarse-to-fine framework for open-world 3D scene generation. Planning agents translate a text prompt into a structured specification of regions, terrain, assets, materials, and spatial relations. WorldClaw then builds a globally coherent terrain foundation from semantic layouts, reusable assets, generative or procedural materials, and a region-aware height field. For detail-demanding regions, it generates terrain-conditioned compositions, reconstructs editable textured meshes, and recovers their placement on the terrain; render-based agents further refine terrain, objects, appearance, and contacts. Across diverse open-world prompts, WorldClaw produces large-scale scenes with coherent spatial organization, visually compelling local content, and editable instance-level assets while preserving a consistent global terrain structure.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05248 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:23:31.075Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).