mlsanityData to 14 Oct 2026

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

arXiv 2504.07961 ↗First posted 10 Apr 2025cs.CVcited by 67

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

Abstract (arXiv)

We introduce Geo4D, a method to repurpose video diffusion models for monocular 3D reconstruction of dynamic scenes. By leveraging the strong dynamic priors captured by large-scale pre-trained video models, Geo4D can be trained using only synthetic data while generalizing well to real data in a zero-shot manner. Geo4D predicts several complementary geometric modalities, namely point, disparity, and ray maps. We propose a new multi-modal alignment algorithm to align and fuse these modalities, as well as a sliding window approach at inference time, thus enabling robust and accurate 4D reconstruction of long videos. Extensive experiments across multiple benchmarks show that Geo4D significantly surpasses state-of-the-art video depth estimation methods.

Key facts. Cited by 67 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 98 of its 116 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

98 of 116 references.

Closest ancestors · 25

Same direction, newest first

  1. 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors1 Apr
  2. 2025Bolt3D: Generating 3D Scenes in Seconds18 Mar
  3. 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation22 Jan
  4. 2024World-consistent Video Diffusion with Explicit 3D Modeling2 Dec
  5. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis3 Sep
  6. 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusion16 Jul
  7. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priors3 Jun
  8. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  9. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models18 Mar
  10. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image18 Mar
  11. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  12. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D28 Nov
13 more
  1. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  2. 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image27 Oct
  3. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  4. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  5. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  6. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation2 Jun
  7. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  8. 2023Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion20 Apr
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  10. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  11. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  12. 2022Novel View Synthesis with Diffusion Models6 Oct
  13. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 73

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  7. 2022Video Diffusion Modelscited by 2,305
  8. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  9. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  10. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  11. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  12. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
38 more
  1. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  2. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  3. 2024Depth Anything V2cited by 1,422
  4. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  5. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  6. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  8. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  9. 2020Convolutional Occupancy Networkscited by 761
  10. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  13. 2023ModelScope Text-to-Video Technical Reportcited by 658
  14. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  15. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  16. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  17. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  18. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 471
  19. 2023VideoComposer: Compositional Video Synthesis with Motion Controllabilitycited by 464
  20. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  21. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  22. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  23. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  24. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  25. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  26. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generationcited by 302
  27. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  28. 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Modelscited by 285
  29. 20243D Reconstruction with Spatial Memorycited by 277
  30. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  31. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 269
  32. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
  33. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  34. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 228
  35. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  36. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  37. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  38. 2020Robust Consistent Video Depth Estimationcited by 188

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 34; 2026: 33.

67 papers.

Sort:

By area:

  1. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  2. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  3. 2025SceneGen: Single-Image 3D Scene Generation in One Feedforward Passcited by 54
  4. 2025Efficiently Reconstructing Dynamic Scenes One D4RT at a Timecited by 54
  5. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  6. 2025DeepVerse: 4D Autoregressive Video Generation as a World Modelcited by 40
  7. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 35
  8. 20254DNeX: Feed-Forward 4D Generative Modeling Made Easycited by 34
  9. 2026V-DPM: 4D Video Reconstruction with Dynamic Point Mapscited by 34
  10. 2025VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstructioncited by 28
  11. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  12. 2025Epipolar Geometry Improves Video Generation Modelscited by 26
38 more
  1. 2026VGGT-Omegacited by 26
  2. 2026VGGRPO: Towards World-Consistent Video Generation with 4D Latent Rewardcited by 24
  3. 2025PlayerOne: Egocentric World Simulatorcited by 20
  4. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  5. 2025GeoVideo: Introducing Geometric Regularization into Video Generation Modelcited by 19
  6. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 18
  7. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  8. 2026Video Generation Models are General-Purpose Vision Learnerscited by 14
  9. 2026Track4World: Feedforward World-centric Dense 3D Tracking of All Pixelscited by 13
  10. 2026Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Videocited by 12
  11. 2025How Much 3D Do Video Foundation Models Encode?cited by 11
  12. 20254D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimationcited by 10
  13. 2025VGGT-X: When VGGT Meets Dense Novel View Synthesiscited by 8
  14. 2025PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perceptioncited by 8
  15. 2025One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Controlcited by 8
  16. 2025EgoX: Egocentric Video Generation from a Single Exocentric Videocited by 8
  17. 2025UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generationcited by 7
  18. 2026GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generatorcited by 7
  19. 2025CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusioncited by 6
  20. 2025WorldReel: 4D Video Generation with Consistent Geometry and Motion Modelingcited by 5
  21. 2026THFM: A Unified Video Foundation Model for 4D Human Perception and Beyondcited by 5
  22. 2026TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Trackingcited by 5
  23. 2025RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenescited by 4
  24. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  25. 2026FrameCrafter: Novel View Synthesis as Video Completioncited by 4
  26. 2026Syn4D: A Multiview Synthetic 4D Datasetcited by 4
  27. 2026GeoStream: Toward Precise Camera Controlled Streaming Video Generationcited by 4
  28. 2026HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesiscited by 4
  29. 2025Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstructioncited by 3
  30. 2025Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generationcited by 3
  31. 2025HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videoscited by 3
  32. 2026EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesiscited by 3
  33. 2026MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAEcited by 3
  34. 2026SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenescited by 3
  35. 2026ViPS: Video-informed Pose Spaces for Auto-Rigged Meshescited by 3
  36. 2026GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformerscited by 3
  37. 2025DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relightingcited by 2
  38. 2025Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generationcited by 2

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Can Video Diffusion Model Reconstruct 4D Geometry?
  2. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
  3. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
  4. 2026Alignment Is All You Need For X-to-4D Generation
  5. 2025UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
  6. 2025Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
  7. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
  8. 2023Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image