WonderZoom: Multi-Scale 3D World Generation
Not on the map. Why?
Abstract (arXiv)
We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene contents at varying granularities. The fundamental challenge is the lack of a scale-aware 3D representation capable of generating and rendering content with largely different spatial sizes. WonderZoom addresses this through two key innovations: (1) scale-adaptive Gaussian surfels for generating and real-time rendering of multi-scale 3D scenes, and (2) a progressive detail synthesizer that iteratively generates finer-scale 3D contents. Our approach enables users to "zoom into" a 3D region and auto-regressively synthesize previously non-existent fine details from landscapes to microscopic features. Experiments demonstrate that WonderZoom significantly outperforms state-of-the-art video and 3D models in both quality and alignment, enabling multi-scale 3D world creation from a single image. We show video results and an interactive viewer of generated multi-scale 3D worlds in https://wonderzoom.github.io/
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 51 of its 56 references that are in the map. First posted on arXiv 9 Dec 2025.
Builds on
51 of 56 references.
References · 51
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
- 2021Alias-Free Generative Adversarial Networkscited by 1,181
- 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
- 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
- 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
- 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
38 more
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
- 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
- 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
- 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
- 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
- 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
- 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
- 2020Single-View View Synthesis with Multiplane Imagescited by 263
- 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
- 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
- 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
- 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
- 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
- 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
- 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
- 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
- 2023WonderJourney: Going from Anywhere to Everywherecited by 157
- 20193D Ken Burns Effect from a Single Imagecited by 128
- 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
- 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
- 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
- 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 93
- 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 91
- 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
- 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
- 2024DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splattingcited by 81
- 2023CityDreamer: Compositional Generative Model of Unbounded 3D Citiescited by 75
- 2024DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Samplingcited by 72
- 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
- 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generationcited by 53
- 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
- 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
- 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 43
- 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priorscited by 36
- 2025SynCity: Training-Free Generation of 3D Worldscited by 30
- 2023Dense Pixel-to-Pixel Harmonization via Continuous Image Representationcited by 19
- 2025Compositional Generative Model of Unbounded 4D Citiescited by 16
- 2023Generative Powers of Tencited by 15
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.