mlsanityData to 14 Oct 2026

SynCity: Training-Free Generation of 3D Worlds

arXiv 2503.16420 ↗First posted 20 Mar 2025cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world is generated tile-by-tile, and each new tile is generated within its world-context and then fused with the scene. SynCity generates compelling and immersive scenes that are rich in detail and diversity.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 60 of its 71 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

60 of 71 references.

References · 60

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  6. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  7. 2018Demystifying MMD GANscited by 1,293
  8. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  9. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  10. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  11. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  12. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
38 more
  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  2. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  3. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  4. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  5. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  6. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  7. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  8. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  9. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  10. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  11. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  12. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  13. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  14. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  15. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  16. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 213
  17. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  18. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  19. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  20. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  21. 2023WonderJourney: Going from Anywhere to Everywherecited by 158
  22. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  23. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  24. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 123
  25. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 117
  26. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  27. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109
  28. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 106
  29. 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generationcited by 84
  30. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 83
  31. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  32. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  33. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  34. 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 76
  35. 2023Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenescited by 75
  36. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 73
  37. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  38. 20233D-aware Image Generation using 2D Diffusion Modelscited by 69

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 16.

31 papers.

Sort:

By area:

  1. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 44
  2. 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
  3. 20253D Scene Generation: A Surveycited by 24
  4. 2025Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusioncited by 16
  5. 2025WorldGrow: Generating Infinite 3D Worldcited by 16
  6. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  7. 2025Steerable Scene Generation with Post Training and Inference-Time Searchcited by 9
  8. 2025Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansioncited by 9
  9. 2025TRELLISWorld: Training-Free World Generation from Object Generatorscited by 8
  10. 2026WorldClaw: Agentic 3D Open-World Generation at Scalecited by 8
  11. 2025EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusioncited by 6
  12. 2025ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxiescited by 5
19 more
  1. 2025InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexitycited by 5
  2. 2026Extend3D: Town-Scale 3D Generationcited by 5
  3. 2026MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphingcited by 4
  4. 2025Constructing a 3D Scene from a Single Imagecited by 3
  5. 2025Self-Evolving 3D Scene Generation from a Single Imagecited by 3
  6. 2026WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generationcited by 3
  7. 2026Sat2City v2: Native 3D City Asset Generation from a Single Satellite Imagecited by 3
  8. 2026RnG: A Unified Transformer for Complete 3D Modeling from Partial Observationscited by 2
  9. 2026GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generationcited by 2
  10. 2025WonderZoom: Multi-Scale 3D World Generationcited by 1
  11. 2026NuiWorld: Exploring a Scalable Framework for End-to-End Controllable World Generationcited by 1
  12. 2026Map2World: Segment Map Conditioned Text to 3D World Generationcited by 1
  13. 2026StateFlow: Building, Evolving, and Accessing 3D World States for Previsualizationcited by 1
  14. 2026Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Modelscited by 0
  15. 2026Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantificationcited by 0
  16. 2026To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generationcited by 0
  17. 2026GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generationcited by 0
  18. 2026Scaling 3D Generative Priors to Large-Scale Scene Meshes from Multi-View Imagescited by 0
  19. 2026WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D Worldcited by 0