HetScene: 基于异质性的扩散方法用于密集室内场景生成
HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation
AI总结：
本文提出HetScene方法，通过将物体分解为主次物体，解决密集布局和复杂空间依赖的生成问题，提升场景生成的物理合理性和可扩展性。
摘要：
生成可控且物理合理的室内场景是构建高保真模拟环境的关键前提。然而，现有基于深度学习的方法通常将所有物体视为同质实例，在统一生成过程中处理。尽管在稀疏和简单布局上有效，但难以建模密集物体布置和复杂空间依赖，导致可扩展性有限和物理合理性下降。为应对这些挑战，我们从结构异质性的角度重新审视室内布局生成，并根据物体在塑造场景中的不同角色将其分解为主物体和次物体。基于这种分解，我们提出HetScene，一种异质两阶段生成框架，将室内布局合成分解为结构布局生成（SLG）和上下文布局生成（CLG）。SLG首先仅使用主物体生成全局一致的结构布局，基于文本描述、自顶向下的二进制房间掩码和空间关系图，建立稳定的大型核心家具全局骨架。
英文摘要：
Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as homogeneous instances within a unified generation process. While effective for sparse and simplistic layouts, they struggle to model realistic layouts with dense object arrangements and complex spatial dependencies, leadingto limited scalability and degraded physical plausibility. To deal with these challenges, we revisit indoor layout generation from the perspective of structural heterogeneity and decompose the objects into primary objects and secondary objects according to their distinct roles in shaping a scene. Based on this decomposition, we propose HetScene, a heterogeneous two-stage generation framework that decouples indoor layout synthesis into Structural Layout Generation (SLG) and Contextual Layout Generation (CLG). SLG first generates globally coherent structural layouts with only primary objects conditioned on text descriptions, top-down binary room masks, and spatial relation graphs, establishing a stable global macro-skeleton of large core furniture.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
