layout-generation

Architect-Ant 提出 AntPlan 数据集（505 份专业建筑平面图、92 个家具类别）与基于可编辑坐标 DSL 的家具布局生成框架，通过 SFT 与 GRPO（以 Layout Rule Score 为奖励）实现约束感知、可编辑且可转换为 3D 场景的自动室内布置。

Mira-Scene introduces a compositional 3D scene reconstruction framework using pixel-aligned canonical coordinate maps for accurate object layouts, achieving significant improvements in layout accuracy over existing methods.

Function2Scene generates 3D indoor layouts from functional descriptions by parsing user needs and applying design constraints through an iterative refinement loop combining geometric analysis, LLM reasoning, and VLM assessment, outperforming baselines in satisfying functional requirements.

LaviGen is a framework that repurposes 3D generative models for autoregressive 3D layout generation, using an adapted 3D diffusion model with dual-guidance self-rollout distillation to achieve 19% higher physical plausibility and 65% faster computation than state-of-the-art methods on the LayoutVLM benchmark.