SceneBloom：用扩散先验与契约引导编译生成真实室内场景
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
arXiv 上的新工作 SceneBloom，用扩散模型生成可仿真训练的 3D 室内场景，做具身智能的朋友可以看看，代码已开源。
SceneBloom 是一个用于具身智能训练环境的生成框架，先用扩散先验在功能区域内采样家具布局，再通过编译器进行几何拟合和局部姿态校正。在 5 种房间类型上，它的视觉质量和物理稳定性优于对比方法，且是唯一没有网格碰撞和越界物体的方法。其布局分布比所有基线更接近真实房间。在这些场景中训练的物体导航策略，在与真实扫描数量相同的训练条件下，在保留真实扫描上的成功率高于用真实扫描训练的模型。
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
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 https://github.com/Tinaliu0123/scenebloom.