mlsanityData to 14 Oct 2026

Compositional 3D Scene Generation using Locally Conditioned Diffusion

arXiv 2303.12218 ↗First posted 21 Mar 2023cs.CVcited by 101

Not on the map. Why?

Cited by 35 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited to object-level generation. We introduce locally conditioned diffusion as an approach to compositional scene diffusion, providing control over semantic parts using text prompts and bounding boxes while ensuring seamless transitions between these parts. We demonstrate a score distillation sampling--based text-to-3D synthesis pipeline that enables compositional 3D scene generation at a higher fidelity than relevant baselines.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

48 of 56 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  12. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
36 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  3. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  4. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  5. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  6. 2020Neural Sparse Voxel Fieldscited by 959
  7. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  8. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  10. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  11. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 699
  12. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  13. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  14. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  15. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  16. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  17. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  18. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  19. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  20. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  21. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  22. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  23. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  24. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  25. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  26. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 123
  27. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  28. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 112
  29. 2019Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesiscited by 104
  30. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Processcited by 100
  31. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  32. 2021LOLNeRF: Learn from One Lookcited by 84
  33. 2022DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesiscited by 61
  34. 2019HoloGAN: Unsupervised learning of 3D representations from natural imagescited by 59
  35. 2023Mixture of Diffusers for scene composition and high resolution image generationcited by 56
  36. 2022Shape-Guided Diffusion with Inside-Outside Attentioncited by 45

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 20; 2024: 54; 2025: 23; 2026: 4.

101 papers.

Sort:

By area:

  1. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  2. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 166
  3. 2023Video Language Planningcited by 162
  4. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  5. 2023State of the Art on Diffusion Models for Visual Computingcited by 127
  6. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117
  7. 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splattingcited by 109
  8. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 97
  9. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 96
  10. 2024DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splattingcited by 82
  11. 2024TC4D: Trajectory-Conditioned Text-to-4D Generationcited by 77
  12. 2024DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Samplingcited by 72
38 more
  1. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
  2. 2024EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusioncited by 67
  3. 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 62
  4. 2023Generative AI meets 3D: A Survey on Text-to-3D in AIGC Eracited by 61
  5. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  6. 2023Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3Dcited by 59
  7. 2024ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidancecited by 59
  8. 2023ControlRoom3D: Room Generation using Semantic Proxy Roomscited by 56
  9. 2023SceneWiz3D: Towards Text-guided 3D Scene Compositioncited by 54
  10. 2024Generic 3D Diffusion Adapter Using Controlled Multi-View Editingcited by 47
  11. 2024REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignmentcited by 45
  12. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 43
  13. 2024SceneTeller: Language-to-3D Scene Generationcited by 43
  14. 2023CG3D: Compositional Generation for Text-to-3D via Gaussian Splattingcited by 42
  15. 2024SceneCraft: Layout-Guided 3D Scene Generationcited by 41
  16. 2024Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusioncited by 39
  17. 2024Disentangled 3D Scene Generation with Layout Learningcited by 33
  18. 2023Control4D: Efficient 4D Portrait Editing with Textcited by 32
  19. 2023Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Modelscited by 30
  20. 2023Probabilistic Adaptation of Text-to-Video Modelscited by 29
  21. 2025ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediarycited by 28
  22. 2024Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Planecited by 26
  23. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 25
  24. 20253D Scene Generation: A Surveycited by 24
  25. 2024Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketchescited by 21
  26. 2024Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprintcited by 21
  27. 2025WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agentscited by 21
  28. 2023DreamPropeller: Supercharge Text-to-3D Generation with Parallel Samplingcited by 20
  29. 2024Compositional Generative Inverse Designcited by 20
  30. 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 20
  31. 2024PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Imagecited by 19
  32. 2024InterFusion: Text-Driven Generation of 3D Human-Object Interactioncited by 18
  33. 2024Compositional 3D-aware Video Generation with LLM Directorcited by 18
  34. 2023Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedbackcited by 17
  35. 2025HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editingcited by 15
  36. 2023Applications of Large Scale Foundation Models for Autonomous Drivingcited by 14
  37. 2024RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpaintingcited by 14
  38. 2025Agentic 3D Scene Generation with Spatially Contextualized VLMscited by 14

50 most cited of 101 All 101 (JSON)