mlsanityData to 14 Oct 2026

CityDreamer: Compositional Generative Model of Unbounded 3D Cities

arXiv 2309.00610 ↗First posted 1 Sep 2023cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

3D city generation is a desirable yet challenging task, since humans are more sensitive to structural distortions in urban environments. Additionally, generating 3D cities is more complex than 3D natural scenes since buildings, as objects of the same class, exhibit a wider range of appearances compared to the relatively consistent appearance of objects like trees in natural scenes. To address these challenges, we propose CityDreamer, a compositional generative model designed specifically for unbounded 3D cities. Our key insight is that 3D city generation should be a composition of different types of neural fields: 1) various building instances, and 2) background stuff, such as roads and green lands. Specifically, we adopt the bird's eye view scene representation and employ a volumetric render for both instance-oriented and stuff-oriented neural fields. The generative hash grid and periodic positional embedding are tailored as scene parameterization to suit the distinct characteristics of building instances and background stuff. Furthermore, we contribute a suite of CityGen Datasets, including OSM and GoogleEarth, which comprises a vast amount of real-world city imagery to enhance the realism of the generated 3D cities both in their layouts and appearances. CityDreamer achieves state-of-the-art performance not only in generating realistic 3D cities but also in localized editing within the generated cities.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 50 of its 65 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

50 of 65 references.

References · 50

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  10. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  12. 2018Demystifying MMD GANscited by 1,293
38 more
  1. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  2. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  3. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  4. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  5. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  6. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  7. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  8. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  9. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  10. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  11. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  12. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  13. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  14. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  15. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  16. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 158
  17. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  18. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  19. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  20. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 118
  21. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
  22. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  23. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  24. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  25. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  26. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  27. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  28. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  29. 2020World-Consistent Video-to-Video Synthesiscited by 69
  30. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  31. 2021InfinityGAN: Towards Infinite-Pixel Image Synthesiscited by 61
  32. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  33. 20223D-Aware Indoor Scene Synthesis with Depth Priorscited by 32
  34. 2019SpaceNet MVOI: a Multi-View Overhead Imagery Datasetcited by 29
  35. 2020HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structurescited by 29
  36. 2023StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generationcited by 25
  37. 2022OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Imagescited by 21
  38. 2022Towards Better User Studies in Computer Graphics and Visioncited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 17; 2025: 33; 2026: 21.

76 papers.

Sort:

By area:

  1. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 261
  2. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  3. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
  4. 2023ADriver-I: A General World Model for Autonomous Drivingcited by 104
  5. 20243DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priorscited by 74
  6. 2024InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Modelscited by 56
  7. 2023Pyramid Diffusion for Fine 3D Large Scene Generationcited by 44
  8. 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 44
  9. 2025SynCity: Training-Free Generation of 3D Worldscited by 31
  10. 2024A Comprehensive Survey on 3D Content Generationcited by 28
  11. 2024LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitivescited by 26
  12. 2024CityCraft: A Real Crafter for 3D City Generationcited by 26
38 more
  1. 2025StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generationcited by 26
  2. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 25
  3. 2024UrbanWorld: An Urban World Model for 3D City Generationcited by 24
  4. 20253D Scene Generation: A Surveycited by 24
  5. 2023CityGen: Infinite and Controllable City Layout Generationcited by 22
  6. 2024CityX: Controllable Procedural Content Generation for Unbounded 3D Citiescited by 22
  7. 2024Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patternscited by 21
  8. 2025X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllabilitycited by 20
  9. 2025NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenescited by 19
  10. 2024Urban Architect: Steerable 3D Urban Scene Generation with Layout Priorcited by 17
  11. 2025Compositional Generative Model of Unbounded 4D Citiescited by 17
  12. 2025Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagerycited by 17
  13. 2025Towards Autonomous Micromobility through Scalable Urban Simulationcited by 16
  14. 2025Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusioncited by 16
  15. 2025WorldGrow: Generating Infinite 3D Worldcited by 16
  16. 2025Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splattingcited by 12
  17. 2024COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generationcited by 10
  18. 2025Controllable 3D Outdoor Scene Generation via Scene Graphscited by 9
  19. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  20. 2025Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansioncited by 9
  21. 2026WorldClaw: Agentic 3D Open-World Generation at Scalecited by 8
  22. 2025Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagerycited by 7
  23. 2024Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussianscited by 6
  24. 2025EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusioncited by 6
  25. 2025MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layoutscited by 6
  26. 20246Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstructioncited by 5
  27. 2025ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxiescited by 5
  28. 2025LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Groundingcited by 5
  29. 2026Imagine a City: CityGenAgent for Procedural 3D City Generationcited by 5
  30. 2026MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstructioncited by 5
  31. 2026Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Imagecited by 5
  32. 2024GroundUp: Rapid Sketch-Based 3D City Massingcited by 4
  33. 2025From 2D to 3D Cognition: A Brief Survey of General World Modelscited by 4
  34. 2025MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusioncited by 3
  35. 2025SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priorscited by 3
  36. 2025CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generationcited by 3
  37. 2025UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scalecited by 3
  38. 2026Sat2City v2: Native 3D City Asset Generation from a Single Satellite Imagecited by 3

50 most cited of 76 All 76 (JSON)