mlsanityData to 7 Oct 2026

ATISS: Autoregressive Transformers for Indoor Scene Synthesis

arXiv 2110.03675 ↗First posted 7 Oct 2021cs.CVcited by 195

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The ability to synthesize realistic and diverse indoor furniture layouts automatically or based on partial input, unlocks many applications, from better interactive 3D tools to data synthesis for training and simulation. In this paper, we present ATISS, a novel autoregressive transformer architecture for creating diverse and plausible synthetic indoor environments, given only the room type and its floor plan. In contrast to prior work, which poses scene synthesis as sequence generation, our model generates rooms as unordered sets of objects. We argue that this formulation is more natural, as it makes ATISS generally useful beyond fully automatic room layout synthesis. For example, the same trained model can be used in interactive applications for general scene completion, partial room re-arrangement with any objects specified by the user, as well as object suggestions for any partial room. To enable this, our model leverages the permutation equivariance of the transformer when conditioning on the partial scene, and is trained to be permutation-invariant across object orderings. Our model is trained end-to-end as an autoregressive generative model using only labeled 3D bounding boxes as supervision. Evaluations on four room types in the 3D-FRONT dataset demonstrate that our model consistently generates plausible room layouts that are more realistic than existing methods. In addition, it has fewer parameters, is simpler to implement and train and runs up to 8 times faster than existing methods.

Key facts. Cited by 195 papers in the map (data through 7 Oct 2026). Builds on 58 of its 92 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

58 of 92 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2020Language Models are Few-Shot Learnerscited by 32,199
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2013Auto-Encoding Variational Bayescited by 3,980
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
38 more
  1. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  8. 2018Self-Attention with Relative Position Representationscited by 1,112
  9. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  10. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  11. 2018Image Transformercited by 770
  12. 2020Jukebox: A Generative Model for Musiccited by 535
  13. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  14. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  15. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  16. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  17. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  18. 2017Grammar Variational Autoencodercited by 283
  19. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  20. 2019Cross-Modal Self-Attention Network for Referring Image Segmentationcited by 263
  21. 2018Scaling Neural Machine Translationcited by 204
  22. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  23. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  24. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 154
  25. 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 129
  26. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  27. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  28. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  29. 2018Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Modelscited by 105
  30. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  31. 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
  32. 2021An Image is Worth 16x16 Words, What is a Video Worth?cited by 87
  33. 2018Human-centric Indoor Scene Synthesis Using Stochastic Grammarcited by 73
  34. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  35. 2018Deep Generative Modeling for Scene Synthesis via Hybrid Representationscited by 63
  36. 2020Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generationcited by 58
  37. 2019SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentationcited by 55
  38. 2020End-to-end Contextual Perception and Prediction with Interaction Transformercited by 54

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 28; 2024: 40; 2025: 59; 2026: 53.

195 papers.

Sort:

By area:

  1. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  2. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  3. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
  4. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  5. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 141
  6. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  7. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  8. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
  9. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 113
  10. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 110
  11. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 94
  12. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
38 more
  1. 2024I-Design: Personalized LLM Interior Designercited by 87
  2. 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 81
  3. 2023LEGO-Net: Learning Regular Rearrangements of Objects in Roomscited by 75
  4. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 75
  5. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  6. 2024EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusioncited by 66
  7. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 66
  8. 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 65
  9. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 59
  10. 2023CC3D: Layout-Conditioned Generation of Compositional 3D Scenescited by 58
  11. 2022MIME: Human-Aware 3D Scene Generationcited by 57
  12. 2022Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Imagecited by 55
  13. 2023CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusioncited by 54
  14. 2023RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texturecited by 53
  15. 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agentcited by 53
  16. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
  17. 2024Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databasescited by 43
  18. 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 43
  19. 2024SceneTeller: Language-to-3D Scene Generationcited by 43
  20. 2026SAGE: Scalable Agentic 3D Scene Generation for Embodied AIcited by 40
  21. 2023SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometrycited by 38
  22. 2024Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpaintingcited by 37
  23. 2024LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Modelcited by 34
  24. 2025MetaScenes: Towards Automated Replica Creation for Real-world 3D Scanscited by 31
  25. 2024Mixed Diffusion for 3D Indoor Scene Synthesiscited by 30
  26. 2025Global-Local Tree Search in VLMs for 3D Indoor Scene Generationcited by 29
  27. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 27
  28. 2025ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediarycited by 27
  29. 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoningcited by 27
  30. 2024Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Planecited by 26
  31. 2025SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesiscited by 26
  32. 2023NAP: Neural 3D Articulation Priorcited by 25
  33. 2022Learning 3D Scene Priors with 2D Supervisioncited by 24
  34. 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
  35. 2024SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generationcited by 24
  36. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 24
  37. 20253D Scene Generation: A Surveycited by 24
  38. 2025FlairGPT: Repurposing LLMs for Interior Designscited by 22

50 most cited of 195 All 195 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025RoomCraft: Controllable and Complete 3D Indoor Scene Generation
  2. 2026HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes
  3. 2026SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
  4. 2024SceneCraft: Layout-Guided 3D Scene Generation
  5. 2025Text To 3D Object Generation For Scalable Room Assembly
  6. 2025MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models
  7. 2026SceneCritic: A Symbolic Evaluator for 3D Indoor Scene Synthesis
  8. 2026SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-turn RL