Metraipolis › archive › dc_7b57c57096fa
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning — arXiv:2610.32978
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32978
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:52:43.816Z
- SHA-256 of the archived text
1bc038940a9d7909f346bd08105ddf6206c2d982f3ed26c302ed71097b4be635- Stable URL of this page
https://metraipolis.com/documento/dc_7b57c57096fa
How to cite
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning — arXiv:2610.32978 — arXiv (en), https://arxiv.org/abs/2610.32978 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b57c57096fa (Metraipolis archive dc_7b57c57096fa, sha256 1bc038940a9d7909f346bd08105ddf6206c2d982f3ed26c302ed71097b4be635)
BibTeX
@misc{dc7b57c57096fa,
title = {SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning — arXiv:2610.32978},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32978},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b57c57096fa; sha256 1bc038940a9d7909f346bd08105ddf6206c2d982f3ed26c302ed71097b4be635},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32978. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Visual generative models offer rich priors over plausible arrangements, yet their outputs require geometric reasoning to become physically valid 3D scenes. We introduce SceneBloom, an agentic framework that combines visual layout sampling with contract-guided 3D compilation. A hierarchical sampler uses diffusion priors to generate furniture arrangements within functional zones. A compiler then uses relations extracted from each proposal to guide geometric fitting and local pose correction. Across five room types, SceneBloom attains the highest visual quality and physical stability among the compared methods and is the only method with no detected mesh collisions and out-of-bounds objects. Its layouts are also closer to the distribution of real rooms than those of all compared baselines. Object navigation policies trained in these realistic scenes achieve a higher success rate in held-out real scans than those trained on an equal number of real training scans. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.32978 — 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 2026-10-26T19:45:33.445Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).