{"slug": "scenebloom-agentic-indoor-environment-generation-with-realistic-and-diverse-for", "title": "SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning", "summary": "A paper submitted to arXiv on 23 Oct 2026 introduces SceneBloom, an agentic framework that pairs diffusion-based visual layout sampling with contract-guided 3D compilation to generate simulation-ready indoor environments for embodied-agent training. Across five room types, SceneBloom achieved the highest visual quality and physical stability among compared methods and was the only method with no detected mesh collisions or out-of-bounds objects, with layouts closer to the distribution of real rooms than all baselines. Object navigation policies trained in SceneBloom's generated scenes reached a higher success rate on held-out real scans than policies trained on an equal number of real training scans, and code is available on GitHub.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n  [Submitted on 23 Oct 2026]\n\n# Title:SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning\n\n[View PDF](http://arxiv.org/pdf/2610.32978v1)\n\nAbstract: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](https://github.com/Tinaliu0123/scenebloom).\n    \n\n### Additional Features\n\n### Current browse context:\n\ncs.CV\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/scenebloom-agentic-indoor-environment-generation-with-realistic-and-diverse-for", "canonical_source": "http://arxiv.org/abs/2610.32978v1", "published_at": "2026-10-26 14:15:51+00:00", "updated_at": "2026-10-26 14:45:40.672462+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-research", "robotics", "generative-ai"], "entities": ["SceneBloom", "arXiv", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/scenebloom-agentic-indoor-environment-generation-with-realistic-and-diverse-for", "markdown": "https://wpnews.pro/news/scenebloom-agentic-indoor-environment-generation-with-realistic-and-diverse-for.md", "text": "https://wpnews.pro/news/scenebloom-agentic-indoor-environment-generation-with-realistic-and-diverse-for.txt", "jsonld": "https://wpnews.pro/news/scenebloom-agentic-indoor-environment-generation-with-realistic-and-diverse-for.jsonld"}}