SceneBloom：面向具身学习的智能体室内环境生成框架，布局真实多样
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
AI 导读
SceneBloom 是一个结合视觉布局采样与契约引导 3D 编译的智能体框架，用扩散先验在功能分区生成家具布置，再通过几何拟合与局部姿态校正生成物理有效的 3D 场景。在五类房间上，其视觉质量与物理稳定性最优，且是唯一无网格碰撞和越界物体的方法。在这些场景训练的目标导航策略，在真实扫描测试集上的成功率高于同等数量真实训练扫描训练的策略。
正文 · 原文
Abstract: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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.32978 [cs.CV] |
| (or arXiv:2610.32978v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32978 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuhan Liu [view email]
[v1]
Fri, 23 Oct 2026 17:59:21 UTC (3,507 KB)
来源：arXiv cs.AI · arxiv.org