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

• URL: http://arxiv.org/abs/2506.05341v1
• Date: Thu, 05 Jun 2025 17:59:42 GMT
• Title: Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
• Authors: Xingjian Ran, Yixuan Li, Linning Xu, Mulin Yu, Bo Dai,
• Abstract summary: 3D indoor scene synthesis is vital for embodied AI and digital content creation.<n>Existing methods fail to generate scenes that are both open-vocabulary and aligned with fine-grained user instructions.<n>We introduce Direct, a framework that directly generates numerical 3D layouts from text descriptions.
• Score: 27.872834485482276
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• RoomCraft: Controllable and Complete 3D Indoor Scene Generation [51.19602078504066]
  RoomCraft is a multi-stage pipeline that converts real images, sketches, or text descriptions into coherent 3D indoor scenes.<n>Our approach combines a scene generation pipeline with a constraint-driven optimization framework.<n>RoomCraft significantly outperforms existing methods in generating realistic, semantically coherent, and visually appealing room layouts.
  arXiv  Detail & Related papers  (2025-06-27T15:03:17Z)
• PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Scenes [30.417675568919552]
  Large-scale 3D semantic scene generation has predominantly relied on voxel-based representations.<n> primitives represent semantic entities using compact, coarse 3D structures that are easy to manipulate and compose.<n>PrITTI is a latent diffusion-based framework that leverages primitives as the main foundational elements for generating compositional, controllable, and editable scene layouts.
  arXiv  Detail & Related papers  (2025-06-23T20:47:18Z)
• HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation [50.206100327643284]
  HiScene is a novel hierarchical framework that bridges the gap between 2D image generation and 3D object generation.<n>We generate 3D content that aligns with 2D representations while maintaining compositional structure.
  arXiv  Detail & Related papers  (2025-04-17T16:33:39Z)
• Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors [52.63385546943866]
  We present a text-to-scene generation method (namely, Layout2Scene) using additional semantic layout as the prompt to inject precise control of 3D object positions.<n>To fully leverage 2D diffusion priors in geometry and appearance generation, we introduce a semantic-guided geometry diffusion model and a semantic-geometry guided diffusion model.<n>Our method can generate more plausible and realistic scenes as compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-05T12:20:13Z)
• LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models [57.92316645992816]
  Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space.<n>We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs)<n>We demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve their reasoning performance.
  arXiv  Detail & Related papers  (2024-12-03T06:15:04Z)
• Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting [47.014044892025346]
  Architect is a generative framework that creates complex and realistic 3D embodied environments leveraging diffusion-based 2D image inpainting. Our pipeline is further extended to a hierarchical and iterative inpainting process to continuously generate placement of large furniture and small objects to enrich the scene.
  arXiv  Detail & Related papers  (2024-11-14T22:15:48Z)
• InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior [23.536285325566013]
  Comprehending natural language instructions is a charming property for both 2D and 3D layout synthesis systems. Existing methods implicitly model object joint distributions and express object relations, hindering generation's controllability synthesis systems. We introduce Instruct, a novel generative framework that integrates a semantic graph prior and a layout decoder.
  arXiv  Detail & Related papers  (2024-07-10T12:13:39Z)
• LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model [58.24851949945434]
  LLplace is a novel 3D indoor scene layout designer based on lightweight fine-tuned open-source LLM Llama3. LLplace circumvents the need for spatial relationship priors and in-context exemplars, enabling efficient and credible room layout generation. Our approach demonstrates that LLplace can effectively generate and edit 3D indoor layouts interactively and outperform existing methods in delivering high-quality 3D design solutions.
  arXiv  Detail & Related papers  (2024-06-06T08:53:01Z)
• Planner3D: LLM-enhanced graph prior meets 3D indoor scene explicit regularization [31.52569918586902]
  3D scene synthesis has diverse applications across a spectrum of industries such as robotics, films, and video games. In this paper, we aim at generating realistic and reasonable 3D indoor scenes from scene graph. Our method achieves better 3D scene synthesis, especially in terms of scene-level fidelity.
  arXiv  Detail & Related papers  (2024-03-19T15:54:48Z)
• GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting [52.150502668874495]
  We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing.
  arXiv  Detail & Related papers  (2024-02-11T13:40:08Z)
• LucidDreaming: Controllable Object-Centric 3D Generation [10.646855651524387]
  We present a pipeline capable of spatial and numerical control over 3D generation from only textual prompt commands or 3D bounding boxes. LucidDreaming achieves superior results in object placement precision and generation fidelity compared to current approaches.
  arXiv  Detail & Related papers  (2023-11-30T18:55:23Z)
• LayoutTransformer: Layout Generation and Completion with Self-attention [105.21138914859804]
  We address the problem of scene layout generation for diverse domains such as images, mobile applications, documents, and 3D objects. We propose LayoutTransformer, a novel framework that leverages self-attention to learn contextual relationships between layout elements. Our framework allows us to generate a new layout either from an empty set or from an initial seed set of primitives, and can easily scale to support an arbitrary of primitives per layout.
  arXiv  Detail & Related papers  (2020-06-25T17:56:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.