mlsanityData to 7 Oct 2026

Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models

arXiv 1811.12463 ↗First posted 29 Nov 2018cs.CV cs.GRcited by 105

Not on the map. Why?

Abstract (arXiv)

We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models. Our method operates on a top-down image-based representation, and inserts objects iteratively into the scene by predicting their category, location, orientation and size with separate neural network modules. Our pipeline naturally supports automatic completion of partial scenes, as well as synthesis of complete scenes. Our method is significantly faster than the previous image-based method and generates result that outperforms it and other state-of-the-art deep generative scene models in terms of faithfulness to training data and perceived visual quality.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 11; 2023: 19; 2024: 20; 2025: 22; 2026: 15.

105 papers.

Sort:

By area:

  1. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  2. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  3. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 195
  4. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  5. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  6. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  7. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 110
  8. 2021Variational Transformer Networks for Layout Generationcited by 88
  9. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  10. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  11. 2023LEGO-Net: Learning Regular Rearrangements of Objects in Roomscited by 75
  12. 2023CC3D: Layout-Conditioned Generation of Compositional 3D Scenescited by 58
38 more
  1. 2022MIME: Human-Aware 3D Scene Generationcited by 57
  2. 2023RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texturecited by 53
  3. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
  4. 2024Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databasescited by 43
  5. 2023SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometrycited by 38
  6. 2024LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Modelcited by 34
  7. 2024Mixed Diffusion for 3D Indoor Scene Synthesiscited by 30
  8. 2021Scene Synthesis via Uncertainty-Driven Attribute Synchronizationcited by 29
  9. 2021Indoor Scene Generation from a Collection of Semantic-Segmented Depth Imagescited by 27
  10. 2024Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Planecited by 26
  11. 2025SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesiscited by 26
  12. 2023NAP: Neural 3D Articulation Priorcited by 25
  13. 2022Learning 3D Scene Priors with 2D Supervisioncited by 24
  14. 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
  15. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 24
  16. 20253D Scene Generation: A Surveycited by 24
  17. 2023Category-Level Multi-Part Multi-Joint 3D Shape Assemblycited by 22
  18. 2023CityGen: Infinite and Controllable City Layout Generationcited by 22
  19. 2025FlairGPT: Repurposing LLMs for Interior Designscited by 22
  20. 2025HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generationcited by 22
  21. 2023Scene Synthesis from Human Motioncited by 20
  22. 2024Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLMcited by 20
  23. 2024DeBaRA: Denoising-Based 3D Room Arrangement Generationcited by 20
  24. 2024Neural MP: A Generalist Neural Motion Plannercited by 18
  25. 2023CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embeddingcited by 16
  26. 2023GlobalMapper: Arbitrary-Shaped Urban Layout Generationcited by 15
  27. 2022COFS: Controllable Furniture layout Synthesiscited by 14
  28. 2024PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformerscited by 14
  29. 2021House-GAN++: Generative Adversarial Layout Refinement Networkscited by 13
  30. 2021LUMINOUS: Indoor Scene Generation for Embodied AI Challengescited by 12
  31. 2024Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesiscited by 12
  32. 2025PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformercited by 12
  33. 2022Towards Better User Studies in Computer Graphics and Visioncited by 11
  34. 2023Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptionscited by 11
  35. 2023Language-driven Scene Synthesis using Multi-conditional Diffusion Modelcited by 10
  36. 2024FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenescited by 10
  37. 2024UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarioscited by 10
  38. 2024VRCopilot: Authoring 3D Layouts with Generative AI Models in VRcited by 10

50 most cited of 105 All 105 (JSON)