mlsanityData to 14 Oct 2026

SceneFormer: Indoor Scene Generation with Transformers

arXiv 2012.09793 ↗First posted 17 Dec 2020cs.CVcited by 158

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We address the task of indoor scene generation by generating a sequence of objects, along with their locations and orientations conditioned on a room layout. Large-scale indoor scene datasets allow us to extract patterns from user-designed indoor scenes, and generate new scenes based on these patterns. Existing methods rely on the 2D or 3D appearance of these scenes in addition to object positions, and make assumptions about the possible relations between objects. In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers. We show that our model design leads to faster scene generation with similar or improved levels of realism compared to previous methods. Our method is also flexible, as it can be conditioned not only on the room layout but also on text descriptions of the room, using only the cross-attention mechanism of transformers. Our user study shows that our generated scenes are preferred to the state-of-the-art FastSynth scenes 53.9% and 56.7% of the time for bedroom and living room scenes, respectively. At the same time, we generate a scene in 1.48 seconds on average, 20% faster than FastSynth.

Key facts. Cited by 158 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 16; 2023: 26; 2024: 30; 2025: 38; 2026: 36.

158 papers.

Sort:

By area:

  1. 2021Transformers in Vision: A Surveycited by 1,013
  2. 2021Neural Fields in Visual Computing and Beyondcited by 540
  3. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  4. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 347
  5. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  6. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  7. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  8. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 166
  9. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 137
  10. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  11. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 125
  12. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 117
38 more
  1. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  2. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 93
  3. 2024I-Design: Personalized LLM Interior Designercited by 87
  4. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 83
  5. 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 82
  6. 2023LEGO-Net: Learning Regular Rearrangements of Objects in Roomscited by 76
  7. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 76
  8. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  9. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
  10. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  11. 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 67
  12. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  13. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 60
  14. 2021StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objectscited by 59
  15. 2023CC3D: Layout-Conditioned Generation of Compositional 3D Scenescited by 58
  16. 2022MIME: Human-Aware 3D Scene Generationcited by 57
  17. 2023CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusioncited by 54
  18. 2021ISTR: End-to-End Instance Segmentation with Transformerscited by 52
  19. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  20. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
  21. 2024Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databasescited by 45
  22. 2023SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometrycited by 39
  23. 2024LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Modelcited by 34
  24. 2024Mixed Diffusion for 3D Indoor Scene Synthesiscited by 32
  25. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 30
  26. 2025Global-Local Tree Search in VLMs for 3D Indoor Scene Generationcited by 29
  27. 2025ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediarycited by 28
  28. 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoningcited by 28
  29. 2024CityCraft: A Real Crafter for 3D City Generationcited by 26
  30. 2023NAP: Neural 3D Articulation Priorcited by 25
  31. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 25
  32. 2022Learning 3D Scene Priors with 2D Supervisioncited by 24
  33. 2025HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generationcited by 24
  34. 20253D Scene Generation: A Surveycited by 24
  35. 2022Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustnesscited by 23
  36. 2023Object Detection with Transformers: A Reviewcited by 22
  37. 2024Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLMcited by 21
  38. 2025WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agentscited by 21

50 most cited of 158 All 158 (JSON)