mlsanityData to 14 Oct 2026

EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion

arXiv 2405.00915 ↗First posted 2 May 2024cs.CV cs.AI cs.LGcited by 67

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present EchoScene, an interactive and controllable generative model that generates 3D indoor scenes on scene graphs. EchoScene leverages a dual-branch diffusion model that dynamically adapts to scene graphs. Existing methods struggle to handle scene graphs due to varying numbers of nodes, multiple edge combinations, and manipulator-induced node-edge operations. EchoScene overcomes this by associating each node with a denoising process and enables collaborative information exchange, enhancing controllable and consistent generation aware of global constraints. This is achieved through an information echo scheme in both shape and layout branches. At every denoising step, all processes share their denoising data with an information exchange unit that combines these updates using graph convolution. The scheme ensures that the denoising processes are influenced by a holistic understanding of the scene graph, facilitating the generation of globally coherent scenes. The resulting scenes can be manipulated during inference by editing the input scene graph and sampling the noise in the diffusion model. Extensive experiments validate our approach, which maintains scene controllability and surpasses previous methods in generation fidelity. Moreover, the generated scenes are of high quality and thus directly compatible with off-the-shelf texture generation. Code and trained models are open-sourced.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 54 of its 62 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

54 of 62 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024EscherNet: A Generative Model for Scalable View Synthesis6 Feb
  2. 2023SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors28 Nov
  3. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  4. 2023CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout24 Mar
  5. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Models20 Mar
  6. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  7. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  9. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  10. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  11. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  12. 2018Demystifying MMD GANscited by 1,293
35 more
  1. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  2. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  3. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  4. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 327
  5. 2018Image Generation from Scene Graphscited by 324
  6. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  7. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  8. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 208
  9. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  10. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 199
  11. 20203D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humanscited by 144
  12. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  13. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  14. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  15. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  16. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 117
  17. 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splattingcited by 109
  18. 2023Compositional 3D Scene Generation using Locally Conditioned Diffusioncited by 101
  19. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 97
  20. 2021Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphscited by 84
  21. 2023Autoregressive Diffusion Model for Graph Generationcited by 83
  22. 2020Semantic Image Manipulation Using Scene Graphscited by 82
  23. 2023Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenescited by 75
  24. 2023DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion modelcited by 75
  25. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  26. 2023CC3D: Layout-Conditioned Generation of Compositional 3D Scenescited by 58
  27. 2019SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentationcited by 55
  28. 2020End-to-End Optimization of Scene Layoutcited by 52
  29. 20224D-OR: Semantic Scene Graphs for OR Domain Modelingcited by 49
  30. 2023Scenario Diffusion: Controllable Driving Scenario Generation With Diffusioncited by 47
  31. 2020Semantic Graph Based Place Recognition for 3D Point Cloudscited by 43
  32. 2015Text to 3D Scene Generation with Rich Lexical Groundingcited by 36
  33. 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
  34. 2021Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedurescited by 6
  35. 2022LatentSwap3D: Semantic Edits on 3D Image GANscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 35; 2026: 24.

67 papers.

Sort:

By area:

  1. 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agentcited by 56
  2. 2026SAGE: Scalable Agentic 3D Scene Generation for Embodied AIcited by 50
  3. 2024Mixed Diffusion for 3D Indoor Scene Synthesiscited by 32
  4. 2025SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesiscited by 26
  5. 2025HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generationcited by 24
  6. 20253D Scene Generation: A Surveycited by 24
  7. 2025X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllabilitycited by 20
  8. 2025MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generationcited by 19
  9. 2025HiScene: Creating Hierarchical 3D Scenes with Isometric View Generationcited by 18
  10. 2025LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequencescited by 17
  11. 2024EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editingcited by 15
  12. 2025CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Designcited by 14
38 more
  1. 2024DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereocited by 12
  2. 2024Diffusion Models in 3D Vision: A Surveycited by 11
  3. 2025FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Imagescited by 10
  4. 2025La La LiDAR: Large-Scale Layout Generation from LiDAR Datacited by 10
  5. 2024HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Modelcited by 9
  6. 2025Controllable 3D Outdoor Scene Generation via Scene Graphscited by 9
  7. 2025RoomCraft: Controllable and Complete 3D Indoor Scene Generationcited by 9
  8. 2025FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Promptscited by 8
  9. 2025Video Perception Models for 3D Scene Synthesiscited by 7
  10. 2025REACT3D: Recovering Articulations for Interactive Physical 3D Scenescited by 7
  11. 2025ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editingcited by 6
  12. 2025Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimizationcited by 6
  13. 2025SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesiscited by 6
  14. 2025M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generationcited by 6
  15. 2026Engine-Native Editable 3D World Reconstruction with Objects and Lightingcited by 6
  16. 2025PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Taskscited by 5
  17. 2025Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectorscited by 5
  18. 2026FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flowcited by 5
  19. 20253D Software Synthesis Driven by Constraint-Expressive Intermediate Representationcited by 4
  20. 2025HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generationcited by 4
  21. 20263D Scene Graphs: Open Challenges and Future Directionscited by 4
  22. 2024S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Fieldcited by 3
  23. 2025Constructing a 3D Scene from a Single Imagecited by 3
  24. 2025Self-Evolving 3D Scene Generation from a Single Imagecited by 3
  25. 2026SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequencescited by 3
  26. 2026Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editingcited by 3
  27. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2
  28. 2025Learning to Generate 4D LiDAR Sequencescited by 2
  29. 2026SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesiscited by 2
  30. 2024Geometric Algebra Meets Large Language Models: Instruction-Based Transformations of Separate Meshes in 3D, Interactive and Controllable Scenescited by 1
  31. 2025AccioScene: Compositional 3D Scene Generation via Graph Diffusion and Interaction-driven Criticscited by 1
  32. 2025SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulationcited by 1
  33. 2025Generative Data Augmentation for Object Point Cloud Segmentationcited by 1
  34. 2025PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenescited by 1
  35. 2025GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesiscited by 1
  36. 2026Cog2Gen3D: Sculpturing 3D Semantic-Geometric Cognition for 3D Generationcited by 1
  37. 2026Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flowcited by 1
  38. 2026Pair2Scene: Learning Local Object Relations for Procedural Scene Generationcited by 1

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
  2. 2023CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
  3. 2025MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models
  4. 20233D Scene Diffusion Guidance using Scene Graphs
  5. 2023DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation
  6. 2025SPATIALGEN: Layout-guided 3D Indoor Scene Generation
  7. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
  8. 2026Dependency-Aware Discrete Diffusion for Scene Graph Generation