CasLayout：基于级联3D布局扩散的室内场景合成与隐式关系建模
CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
AI总结：
CasLayout通过级联扩散框架将场景生成分解为四个阶段，结合物理与语义约束，提升生成效率与可控性，实现高质量室内场景合成。
摘要：
合成逼真3D室内场景仍面临数据稀缺和同时满足全局建筑约束与局部语义一致性困难的挑战。现有方法常忽略结构边界或依赖全连接关系图导致冗余生成误差。受人类设计认知启发，我们提出CasLayout，一种级联扩散框架，将联合场景生成任务分解为四个具有显式物理和语义作用的条件子阶段：(1)预测家具数量和类别，(2)细化物体尺寸和特征嵌入，(3)在潜在空间建模空间关系，(4)生成定向包围盒(OBBs)。这种解耦架构降低了数据需求，并允许灵活集成大语言模型(LLMs)和视觉语言模型(VLMs)以执行零样本任务如图像到场景生成。为在复杂平面图中保持物理有效性，我们显式将建筑元素(如墙、门和窗)作为条件约束。此外，为解决密集关系图的高熵问题，我们引入与人类空间描述一致的稀疏关系图形式。通过使用双向变分自编码器(VAE)将这些稀疏图编码到紧凑的潜在空间中，所提出的框架提供了增强的关系可控性，使生成的布局更好地遵循功能组织。实验表明，CasLayout在保真度和多样性方面实现了最先进的性能，同时在实际应用中实现了改进的可控性。
英文摘要：
Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors. Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). This decoupled architecture reduces data requirements and enables flexible integration of Large Language Models (LLMs) and Vision Language Models (VLMs) for zero-shot tasks such as image-to-scene generation. To maintain physical validity within complex floor plans, we explicitly model building elements (e.g., walls, doors, and windows) as conditional constraints. Furthermore, to address the high entropy of dense relation graphs, we introduce a sparse relation graph formulation aligned with human spatial descriptions. By encoding these sparse graphs into a compact latent space using a bidirectional Variational Autoencoder (VAE), the proposed framework provides enhanced relational controllability, allowing generated layouts to better respect functional organization. Experiments demonstrate that CasLayout achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.
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。
