mlsanityData to 14 Oct 2026

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

arXiv 2601.00393 ↗First posted 1 Jan 2026cs.CVcited by 46

On the map: World models → Video-generation world models and simulators

Abstract (arXiv)

In this paper, we propose NeoVerse, a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications. We first identify a common limitation of scalability in current 4D world modeling methods, caused either by expensive and specialized multi-view 4D data or by cumbersome training pre-processing. In contrast, our NeoVerse is built upon a core philosophy that makes the full pipeline scalable to diverse in-the-wild monocular videos. Specifically, NeoVerse features pose-free feed-forward 4D reconstruction, online monocular degradation pattern simulation, and other well-aligned techniques. These designs empower NeoVerse with versatility and generalization to various domains. Meanwhile, NeoVerse achieves state-of-the-art performance in standard reconstruction and generation benchmarks. Our project page is available at https://neoverse-4d.github.io.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Placed in Video-generation world models and simulators, one of 11 directions in World models. Builds on 82 of its 87 references that are in the map. First posted on arXiv 1 Jan 2026.

Builds on

82 of 87 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Models26 Mar
  2. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug

Other references · 80

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  10. 2021Vision Transformers for Dense Predictioncited by 1,803
  11. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  12. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
38 more
  1. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  2. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  3. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  4. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  5. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  6. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  7. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  8. 2025VACE: All-in-One Video Creation and Editingcited by 479
  9. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  10. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  11. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  12. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  13. 2022Kubric: A scalable dataset generatorcited by 381
  14. 2020Virtual KITTI 2cited by 353
  15. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  16. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
  17. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  18. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  19. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 287
  20. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  21. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  22. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  23. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  24. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  25. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  26. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  27. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  28. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  29. 2025Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Controlcited by 185
  30. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  31. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
  32. 2023Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perceptioncited by 167
  33. 2024OmniRe: Omni Urban Scene Reconstructioncited by 161
  34. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  35. 2023UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretrainingcited by 151
  36. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  37. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  38. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 46.

46 papers.

Sort:

By area:

  1. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 44
  2. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 21
  3. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 15
  4. 2026WAM4D: Fast 4D World Action Model via Spatial Register Tokenscited by 15
  5. 2026Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trendscited by 8
  6. 2026Streaming Multi-Agent Autoregressive Diffusion Model with World State Registerscited by 8
  7. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 6
  8. 2026VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesiscited by 6
  9. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  10. 2026World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoningcited by 4
  11. 2026Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolutioncited by 4
  12. 2026WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivitycited by 4
34 more
  1. 2026Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamicscited by 3
  2. 2026Holo-World: Unified Camera, Object and Weather Control for Video World Modelcited by 3
  3. 2026I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generationcited by 2
  4. 2026No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videoscited by 2
  5. 2026Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstructioncited by 2
  6. 2026MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generationcited by 2
  7. 2026OpenLongTail: Generative Scaling of Long-Tail Driving Datacited by 2
  8. 2026Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated Meshcited by 2
  9. 20264DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splattingcited by 2
  10. 2026AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splattingcited by 1
  11. 2026Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioningcited by 1
  12. 2026Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Drivingcited by 1
  13. 2026UniQuery4R: Unified 4D Scene Reconstruction from a Single Querycited by 1
  14. 2026VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstructioncited by 0
  15. 2026ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generationcited by 0
  16. 2026AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyondcited by 0
  17. 2026SpatialBench: Is Your Spatial Foundation Model an All-Round Player?cited by 0
  18. 2026World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Videocited by 0
  19. 2026From Generation to Simulation: How Far Are World Models from Being True Simulators?cited by 0
  20. 2026RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generationcited by 0
  21. 2026FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlowcited by 0
  22. 2026Can 4D Foundation Models Remember?cited by 0
  23. 2026Code Plans, Diffusion Renders: Open-Ended Generative World Modelingcited by 0
  24. 2026RoGSW4RLD: Feed-Forward 4D Gaussian Lifting for Robot World Model Rolloutscited by 0
  25. 2026GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Spacecited by 0
  26. 2026MeteoVerse: Unified Weather-Controllable Video World Modelcited by 0
  27. 2026LongLive-Plug: Once-for-All Distillation for Video Generationcited by 0
  28. 2026ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflectionscited by 0
  29. 2026Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Updatecited by 0
  30. 2026DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed Videocited by 0
  31. 2026Learning to Retrieve: Internalizing Memory Retrieval for Video World Modelscited by 0
  32. 2026Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamicscited by 0
  33. 2026GeoFix: Geometry Fixing for 4D Consistent Generationcited by 0
  34. 20264LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
  2. 2025DeepVerse: 4D Autoregressive Video Generation as a World Model
  3. 2025WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
  4. 20254DNeX: Feed-Forward 4D Generative Modeling Made Easy
  5. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
  6. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
  7. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
  8. 2026Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering