HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation

• URL: http://arxiv.org/abs/2605.13586v1
• Date: Wed, 13 May 2026 14:21:51 GMT
• Title: HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation
• Abstract summary: HetScene is a framework to generate controllable and physically plausible indoor scenes for embodied AI.<n>It decomposes objects into primary objects and secondary objects according to their roles in shaping a scene.<n>It generates globally coherent structural layouts with only primary objects conditioned on text descriptions, top-down binary room masks, and spatial relation graphs.
• Score: 25.696780353190253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling [18.135856965440784]
  Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors.<n>Inspired by human design cognition, we present Cas, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages.<n>Experiments demonstrate that Cas achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.
  arXiv  Detail & Related papers  (2026-04-30T03:18:26Z)
• StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation [72.84181869780627]
  StructDiff is a generative framework based on a single-scale diffusion model for single-image generation.<n>It incorporates 3D positional encoding (PE) as a spatial prior, allowing flexible control over positions, scale, and local details of generated objects.<n>It also demonstrates broad applicability across downstream tasks, such as text-guided image generation, image editing, outpainting, and paint-to-image synthesis.
  arXiv  Detail & Related papers  (2026-04-14T10:55:43Z)
• Pair2Scene: Learning Local Object Relations for Procedural Scene Generation [10.247549170637418]
  Pair2Scene is a novel procedural generation framework that integrates learned local rules with scene hierarchies and physics-based algorithms.<n>We show that our framework outperforms existing methods in generating complex environments that go beyond training data.
  arXiv  Detail & Related papers  (2026-04-13T17:59:55Z)
• PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement [89.35154754765502]
  PhyScensis is an agent-based framework powered by a physics engine to produce physically plausible scene configurations.<n>Our framework preserves strong controllability over fine-grained textual descriptions and numerical parameters.<n> Experimental results show that our method outperforms prior approaches in scene complexity, visual quality, and physical accuracy.
  arXiv  Detail & Related papers  (2026-02-16T17:55:25Z)
• HiGS: Hierarchical Generative Scene Framework for Multi-Step Associative Semantic Spatial Composition [1.9131307324613616]
  We propose HiGS, a hierarchical generative framework for multi-step associative semantic spatial composition.<n>HiGS enables users to iteratively expand scenes by selecting key semantic objects, offering fine-grained control over regions of interest.<n>To support structured and coherent generation, we introduce the Progressive Hierarchical Spatial-Semantic Graph.
  arXiv  Detail & Related papers  (2025-10-31T03:50:47Z)
• 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)
• 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)
• LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts [107.11267074981905]
  We propose a semantically controllable layout-AWare diffusion model, termed LAW-Diffusion. We show that LAW-Diffusion yields the state-of-the-art generative performance, especially with coherent object relations.
  arXiv  Detail & Related papers  (2023-08-13T08:06:18Z)
• Person-in-Context Synthesiswith Compositional Structural Space [59.129960774988284]
  We propose a new problem, textbfPersons in Context Synthesis, which aims to synthesize diverse person instance(s) in consistent contexts. The context is specified by the bounding box object layout which lacks shape information, while pose of the person(s) by keypoints which are sparsely annotated. To handle the stark difference in input structures, we proposed two separate neural branches to attentively composite the respective (context/person) inputs into shared compositional structural space'' This structural space is then decoded to the image space using multi-level feature modulation strategy, and learned in a self
  arXiv  Detail & Related papers  (2020-08-28T14:33:28Z)

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.