mlsanityData to 14 Oct 2026

Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation

arXiv 2506.04225 ↗First posted 4 Jun 2025cs.CVcited by 101

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant progress has been made in generating 3D objects from text or images, creating long-range, 3D-consistent, explorable 3D scenes remains a complex and challenging problem. In this work, we present Voyager, a novel video diffusion framework that generates world-consistent 3D point-cloud sequences from a single image with user-defined camera path. Unlike existing approaches, Voyager achieves end-to-end scene generation and reconstruction with inherent consistency across frames, eliminating the need for 3D reconstruction pipelines (e.g., structure-from-motion or multi-view stereo). Our method integrates three key components: 1) World-Consistent Video Diffusion: A unified architecture that jointly generates aligned RGB and depth video sequences, conditioned on existing world observation to ensure global coherence 2) Long-Range World Exploration: An efficient world cache with point culling and an auto-regressive inference with smooth video sampling for iterative scene extension with context-aware consistency, and 3) Scalable Data Engine: A video reconstruction pipeline that automates camera pose estimation and metric depth prediction for arbitrary videos, enabling large-scale, diverse training data curation without manual 3D annotations. Collectively, these designs result in a clear improvement over existing methods in visual quality and geometric accuracy, with versatile applications.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 36 of its 53 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

36 of 53 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Models18 Mar
  2. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation21 Jan
  3. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale9 Dec
  4. 2024LT3SD: Latent Trees for 3D Scene Diffusion12 Sep
  5. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  6. 2023ReconFusion: 3D Reconstruction with Diffusion Priors5 Dec
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar

Other references · 29

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  3. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  4. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  7. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  8. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  9. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
  10. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  11. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 388
  12. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
17 more
  1. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  2. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  3. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 287
  4. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 251
  5. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  6. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  7. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generationcited by 171
  8. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoisingcited by 139
  9. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attentioncited by 89
  10. 2025VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Controlcited by 84
  11. 2024EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagationcited by 77
  12. 2023DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Videocited by 74
  13. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 73
  14. 2024Allegro: Open the Black Box of Commercial-Level Video Generation Modelcited by 70
  15. 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
  16. 2025A Recipe for Generating 3D Worlds From a Single Imagecited by 13
  17. 2024Toon3D: Seeing Cartoons from New Perspectivescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 30; 2026: 71.

101 papers.

Sort:

By area:

  1. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  2. 2025Controllable Video Generation: A Surveycited by 98
  3. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 96
  4. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 94
  5. 20253D and 4D World Modeling: A Surveycited by 67
  6. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
  7. 2025Hunyuan-GameCraft-2: Instruction-following Interactive Game World Modelcited by 61
  8. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 46
  9. 2025VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memorycited by 42
  10. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  11. 2025FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Predictioncited by 38
  12. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 28
38 more
  1. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  2. 2026WorldCompass: Reinforcement Learning for Long-Horizon World Modelscited by 24
  3. 2025Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Controlcited by 18
  4. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 18
  5. 2025Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview imagescited by 17
  6. 2026Latent Spatial Memory for Video World Modelscited by 17
  7. 2025TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Modelcited by 16
  8. 2026Pathwise Test-Time Correction for Autoregressive Long Video Generationcited by 15
  9. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 15
  10. 2026ReRoPE: Repurposing RoPE for Relative Camera Controlcited by 13
  11. 2026Beyond Pixel Histories: World Models with Persistent 3D Statecited by 13
  12. 2026WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPGcited by 13
  13. 2025DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generationcited by 11
  14. 2025How Much 3D Do Video Foundation Models Encode?cited by 11
  15. 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generationcited by 11
  16. 2025Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxycited by 9
  17. 2026PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generationcited by 9
  18. 2025EgoX: Egocentric Video Generation from a Single Exocentric Videocited by 8
  19. 2026Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Contextcited by 8
  20. 2026World Reconstruction From Inconsistent Viewscited by 8
  21. 2025Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Modelscited by 7
  22. 2026InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Modelcited by 7
  23. 2026VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignmentcited by 7
  24. 2026VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modelingcited by 7
  25. 2025CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusioncited by 6
  26. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6
  27. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 6
  28. 2026ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Modelscited by 6
  29. 2026WorldCache: Accelerating World Models for Free via Heterogeneous Token Cachingcited by 6
  30. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  31. 2025Captain Safari: A World Engine with Pose-Aligned 3D Memorycited by 5
  32. 2025SeeU: Seeing the Unseen World via 4D Dynamics-aware Generationcited by 5
  33. 2025WorldReel: 4D Video Generation with Consistent Geometry and Motion Modelingcited by 5
  34. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  35. 2026EgoCS-400K: An Egocentric Gameplay Dataset for World Modelscited by 5
  36. 2025Terra: Explorable Native 3D World Model with Point Latentscited by 4
  37. 2026Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Videocited by 4
  38. 2026WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivitycited by 4

50 most cited of 101 All 101 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024V3D: Video Diffusion Models are Effective 3D Generators
  2. 2024World-consistent Video Diffusion with Explicit 3D Modeling
  3. 2025WorldExplorer: Towards Generating Fully Navigable 3D Scenes
  4. 2025DreamJourney: Perpetual View Generation with Video Diffusion Models
  5. 2026UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
  6. 2025ChronosObserver: Taming 4D World with Hyperspace Diffusion Sampling
  7. 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion
  8. 2026ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space