mlsanityData to 14 Oct 2026

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds

arXiv 2504.02261 ↗First posted 3 Apr 2025cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences. However, a critical challenge in current 3D generation technologies lies in achieving real-time interactivity. To address this issue, we introduce WonderTurbo, the first real-time interactive 3D scene generation framework capable of generating novel perspectives of 3D scenes within 0.72 seconds. Specifically, WonderTurbo accelerates both geometric and appearance modeling in 3D scene generation. In terms of geometry, we propose StepSplat, an innovative method that constructs efficient 3D geometric representations through dynamic updates, each taking only 0.26 seconds. Additionally, we design QuickDepth, a lightweight depth completion module that provides consistent depth input for StepSplat, further enhancing geometric accuracy. For appearance modeling, we develop FastPaint, a 2-steps diffusion model tailored for instant inpainting, which focuses on maintaining spatial appearance consistency. Experimental results demonstrate that WonderTurbo achieves a remarkable 15X speedup compared to baseline methods, while preserving excellent spatial consistency and delivering high-quality output.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 67 of its 81 references that are in the map. First posted on arXiv 3 Apr 2025.

Builds on

67 of 81 references.

References · 67

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  11. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  12. 2020Knowledge Distillation: A Surveycited by 1,603
38 more
  1. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  2. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  3. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  4. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  5. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  6. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  7. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  8. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  9. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  10. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  11. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  12. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  13. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  14. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  15. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  16. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 261
  17. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  18. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  19. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  20. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 221
  21. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  22. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  23. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  24. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  25. 2023WonderJourney: Going from Anywhere to Everywherecited by 158
  26. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 156
  27. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 150
  28. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  29. 20193D Ken Burns Effect from a Single Imagecited by 128
  30. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 123
  31. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representationcited by 123
  32. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 116
  33. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109
  34. 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 89
  35. 2024ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restorationcited by 89
  36. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  37. 2024DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Samplingcited by 72
  38. 2024InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Priorcited by 56

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 18; 2026: 14.

32 papers.

Sort:

By area:

  1. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 139
  2. 2025Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewscited by 65
  3. 2025VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Predictioncited by 48
  4. 2026ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrievalcited by 41
  5. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 32
  6. 2025HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrievalcited by 32
  7. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  8. 2026INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrievalcited by 26
  9. 20253D Scene Generation: A Surveycited by 24
  10. 2026HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrievalcited by 24
  11. 2025WorldGen: From Text to Traversable and Interactive 3D Worldscited by 19
  12. 2025DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusioncited by 15
20 more
  1. 2025HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restorationcited by 13
  2. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  3. 2026Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trendscited by 8
  4. 2026WorldClaw: Agentic 3D Open-World Generation at Scalecited by 8
  5. 2025WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Explorationcited by 7
  6. 2025FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Textcited by 7
  7. 2025IDCNet: Guided Video Diffusion for Metric-Consistent RGBD Scene Generation with Precise Camera Controlcited by 7
  8. 2025CATCH: A Modular Cross-domain Adaptive Template with Hookcited by 6
  9. 2026VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesiscited by 6
  10. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  11. 2026ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulationcited by 6
  12. 2025RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generationcited by 5
  13. 2025Captain Safari: A World Engine with Pose-Aligned 3D Memorycited by 5
  14. 2025Neural-Driven Image Editingcited by 4
  15. 2026GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusioncited by 2
  16. 2026Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusioncited by 2
  17. 2025NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfoldingcited by 1
  18. 2026Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenescited by 1
  19. 2026MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Modelscited by 1
  20. 2026UBATrack: Spatio-Temporal State Space Model for General Multi-Modal Trackingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Recent Advances in 3D Object and Scene Generation: A Survey
  2. 2025WorldGrow: Generating Infinite 3D World
  3. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
  4. 2024PaintScene4D: Consistent 4D Scene Generation from Text Prompts
  5. 2026Interact3D: Compositional 3D Generation of Interactive Objects
  6. 2025A Recipe for Generating 3D Worlds From a Single Image
  7. 2025GEN3D: Generating Domain-Free 3D Scenes from a Single Image
  8. 2026WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes