# Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning

arXiv: https://arxiv.org/abs/2506.05341 · HTML: https://mlsanity.com/paper/2506.05341/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [SceneFormer: Indoor Scene Generation with Transformers](https://mlsanity.com/paper/2012.09793/) (2020)
- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step](https://mlsanity.com/paper/2501.13926/) (2025)
- [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://mlsanity.com/paper/2402.04717/) (2024)
- [GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting](https://mlsanity.com/paper/2402.07207/) (2024)
- [GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs](https://mlsanity.com/paper/2312.00093/) (2023)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [I-Design: Personalized LLM Interior Designer](https://mlsanity.com/paper/2404.02838/) (2024)
- [AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes](https://mlsanity.com/paper/2312.06644/) (2023)
- [SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning](https://mlsanity.com/paper/2501.10074/) (2025)
- [SceneWiz3D: Towards Text-guided 3D Scene Composition](https://mlsanity.com/paper/2312.08885/) (2023)
- [Generative Layout Modeling using Constraint Graphs](https://mlsanity.com/paper/2011.13417/) (2020)
- [Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases](https://mlsanity.com/paper/2403.09675/) (2024)
- [LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model](https://mlsanity.com/paper/2406.03866/) (2024)
- [Global-Local Tree Search in VLMs for 3D Indoor Scene Generation](https://mlsanity.com/paper/2503.18476/) (2025)
- [3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding](https://mlsanity.com/paper/2412.18450/) (2024)
- [LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data](https://mlsanity.com/paper/2202.00185/) (2022)

## Built on by (most cited first, 28 of 28)

- [SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL](https://mlsanity.com/paper/2602.09432/) (2026)
- [InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity](https://mlsanity.com/paper/2511.18200/) (2025)
- [3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing](https://mlsanity.com/paper/2603.22279/) (2026)
- [Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editing](https://mlsanity.com/paper/2603.17583/) (2026)
- [StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics](https://mlsanity.com/paper/2604.03315/) (2026)
- [SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis](https://mlsanity.com/paper/2601.07218/) (2026)
- [SceneCritic: A Symbolic Evaluator for 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2604.13035/) (2026)
- [SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation](https://mlsanity.com/paper/2604.27555/) (2026)
- [HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents](https://mlsanity.com/paper/2606.09738/) (2026)
- [NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation](https://mlsanity.com/paper/2606.29395/) (2026)
- [Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification](https://mlsanity.com/paper/2511.03001/) (2025)
- [GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2511.14884/) (2025)
- [Pair2Scene: Learning Local Object Relations for Procedural Scene Generation](https://mlsanity.com/paper/2604.11808/) (2026)
- [Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion](https://mlsanity.com/paper/2604.16552/) (2026)
- [Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation](https://mlsanity.com/paper/2605.25326/) (2026)
- [Function2Scene: 3D Indoor Scene Layout from Functional Specifications](https://mlsanity.com/paper/2605.30819/) (2026)
- [Global-Local Monte Carlo Tree Search in Vision-Language Models for Text-to-3D Indoor Scene Generation](https://mlsanity.com/paper/2606.06002/) (2026)
- [iARCS: Iterative Agentic RL for Controllable 3D Scene Generation](https://mlsanity.com/paper/2608.06161/) (2026)
- [PARSE: Part-Aware Relational Spatial Modeling](https://mlsanity.com/paper/2603.07704/) (2026)
- [SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions](https://mlsanity.com/paper/2604.01972/) (2026)
- [Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation](https://mlsanity.com/paper/2605.02537/) (2026)
- [Closing the Loop: Unified 3D Scene Generation and Immersive Interaction via LLM-RL Coupling](https://mlsanity.com/paper/2605.05711/) (2026)
- [ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning](https://mlsanity.com/paper/2607.13539/) (2026)
- [SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs](https://mlsanity.com/paper/2608.01106/) (2026)
- [Learning an Interior Layout Policy in a Domain Specific Language Action Space](https://mlsanity.com/paper/2608.07547/) (2026)
- [ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation](https://mlsanity.com/paper/2608.30307/) (2026)
- [SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution](https://mlsanity.com/paper/2609.05594/) (2026)
- [PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking](https://mlsanity.com/paper/2609.21263/) (2026)

## Abstract (arXiv)

Realistic 3D indoor scene synthesis is vital for embodied AI and digital content creation. It can be naturally divided into two subtasks: object generation and layout generation. While recent generative models have significantly advanced object-level quality and controllability, layout generation remains challenging due to limited datasets. Existing methods either overfit to these datasets or rely on predefined constraints to optimize numerical layout that sacrifice flexibility. As a result, they fail to generate scenes that are both open-vocabulary and aligned with fine-grained user instructions. We introduce DirectLayout, a framework that directly generates numerical 3D layouts from text descriptions using generalizable spatial reasoning of large language models (LLMs). DirectLayout decomposes the generation into three stages: producing a Bird's-Eye View (BEV) layout, lifting it into 3D space, and refining object placements. To enable explicit spatial reasoning and help the model grasp basic principles of object placement, we employ Chain-of-Thought (CoT) Activation based on the 3D-Front dataset. Additionally, we design CoT-Grounded Generative Layout Reward to enhance generalization and spatial planning. During inference, DirectLayout addresses asset-layout mismatches via Iterative Asset-Layout Alignment through in-context learning. Extensive experiments demonstrate that DirectLayout achieves impressive semantic consistency, generalization and physical plausibility.