mlsanityData to 7 Oct 2026

SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation

arXiv 2503.16396 ↗First posted 20 Mar 2025cs.CVcited by 44

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

Abstract (arXiv)

We present Stable Video 4D 2.0 (SV4D 2.0), a multi-view video diffusion model for dynamic 3D asset generation. Compared to its predecessor SV4D, SV4D 2.0 is more robust to occlusions and large motion, generalizes better to real-world videos, and produces higher-quality outputs in terms of detail sharpness and spatio-temporal consistency. We achieve this by introducing key improvements in multiple aspects: 1) network architecture: eliminating the dependency of reference multi-views and designing blending mechanism for 3D and frame attention, 2) data: enhancing quality and quantity of training data, 3) training strategy: adopting progressive 3D-4D training for better generalization, and 4) 4D optimization: handling 3D inconsistency and large motion via 2-stage refinement and progressive frame sampling. Extensive experiments demonstrate significant performance gain by SV4D 2.0 both visually and quantitatively, achieving better detail (-14% LPIPS) and 4D consistency (-44% FV4D) in novel-view video synthesis and 4D optimization (-12% LPIPS and -24% FV4D) compared to SV4D. Project page: https://sv4d20.github.io.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 82 of its 88 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

82 of 88 references.

Closest ancestors · 40

Same direction, newest first

  1. 2024SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints10 Dec
  2. 20244Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion5 Dec
  3. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models27 Nov
  4. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion7 Nov
  5. 20243D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation24 Oct
  6. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis3 Sep
  7. 2024CT4D: Consistent Text-to-4D Generation with Animatable Meshes15 Aug
  8. 2024Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle28 Jul
  9. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency24 Jul
  10. 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusion16 Jul
  11. 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models11 Jun
  12. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generation31 May
28 more
  1. 2024EG4D: Explicit Generation of 4D Object without Score Distillation28 May
  2. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models26 May
  3. 2024Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models2 Apr
  4. 2024STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians22 Mar
  5. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  6. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistency28 Dec
  7. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models21 Dec
  8. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation2 Dec
  9. 2023StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D2 Dec
  10. 2023DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling28 Nov
  11. 2023Animate124: Animating One Image to 4D Dynamic Scene24 Nov
  12. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion14 Nov
  13. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  14. 2023ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image27 Oct
  15. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior25 Oct
  16. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model23 Oct
  17. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  18. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models12 Oct
  19. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesis12 Oct
  20. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models4 Oct
  21. 2023SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D4 Oct
  22. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  23. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  24. 2023HoloFusion: Towards Photo-realistic 3D Generative Modeling28 Aug
  25. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  26. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  27. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  28. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  8. 2022Video Diffusion Modelscited by 2,280
  9. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  10. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  11. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  12. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
30 more
  1. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  2. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  3. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  4. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  6. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  7. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  8. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  9. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 307
  10. 2023Text-to-3D using Gaussian Splattingcited by 299
  11. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  12. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  13. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  14. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  15. 2023Text-To-4D Dynamic Scene Generationcited by 204
  16. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 191
  17. 20234D-fy: Text-to-4D Generation Using Hybrid Score Distillation Samplingcited by 184
  18. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  19. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  20. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  21. 2023Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Videocited by 124
  22. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 99
  23. 2019The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentationcited by 95
  24. 2023LEAP: Liberate Sparse-view 3D Modeling from Camera Posescited by 65
  25. 2024GenXD: Generating Any 3D and 4D Scenescited by 49
  26. 2024Vivid-ZOO: Multi-View Video Generation with Diffusion Modelcited by 40
  27. 2023TOSS:High-quality Text-guided Novel View Synthesis from a Single Imagecited by 26
  28. 2023Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clippingcited by 17
  29. 2025AR4D: Autoregressive 4D Generation from Monocular Videoscited by 16
  30. 2024Birth and Death of a Rosecited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 20; 2026: 24.

44 papers.

Sort:

By area:

  1. 2025Puppeteer: Rig and Animate Your 3D Modelscited by 41
  2. 2025DreamArt: Generating Interactable Articulated Objects from a Single Imagecited by 25
  3. 2025ShapeGen4D: Towards High Quality 4D Shape Generation from Videoscited by 20
  4. 2025AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Modelscited by 15
  5. 2026Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesiscited by 15
  6. 2026ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusioncited by 15
  7. 20254D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Timecited by 13
  8. 20254Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generationcited by 12
  9. 2025See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpaintingcited by 11
  10. 2025SS4D: Native 4D Generative Model via Structured Spacetime Latentscited by 7
  11. 2025DIMO: Diverse 3D Motion Generation for Arbitrary Objectscited by 6
  12. 2025Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generationcited by 5
32 more
  1. 2025Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstructioncited by 5
  2. 2026Full-4D: Generating Full-Scope 4D Scenes from a Single-View Videocited by 5
  3. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  4. 2026Choreographing a World of Dynamic Objectscited by 4
  5. 2026FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstructioncited by 4
  6. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  7. 2025FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Bankscited by 3
  8. 20254DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generationcited by 3
  9. 2026HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesiscited by 3
  10. 2025AI-Assisted Rapid Crystal Structure Generation Towards a Target Local Environmentcited by 2
  11. 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infillingcited by 2
  12. 2026Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wildcited by 2
  13. 2025WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wildcited by 1
  14. 2025DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrumcited by 1
  15. 2025SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesiscited by 1
  16. 2025Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generationcited by 1
  17. 2026MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videoscited by 1
  18. 2026MVAnimate: Enhancing Character Animation with Multi-View Optimizationcited by 1
  19. 2026Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generationcited by 1
  20. 2026Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Samplingcited by 1
  21. 2026Fast 4D Mesh Generation by Spatio-Temporal Attention Chainscited by 1
  22. 2026MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcingcited by 1
  23. 2026ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priorscited by 0
  24. 2026Turbo4DGen: Ultra-Fast Acceleration for 4D Generationcited by 0
  25. 2026UNICA: A Unified Neural Framework for Controllable 3D Avatarscited by 0
  26. 2026Velox: Learning Representations of 4D Geometry and Appearancecited by 0
  27. 2026Helix4D: Complex 4D Mesh Generationcited by 0
  28. 2026SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapescited by 0
  29. 2026Progressive Pose-Guided 4D Animal Reconstruction from Monocular Videocited by 0
  30. 2026RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registrationcited by 0
  31. 20264DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humanscited by 0
  32. 20264Director: Controlling Video World Models with Rigid 3D Geometrycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Vid3D: Synthesis of Dynamic 3D Scenes using 2D Video Diffusion
  2. 2025Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency
  3. 2025Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion
  4. 2026Alignment Is All You Need For X-to-4D Generation
  5. 2025Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
  6. 2025SViM3D: Stable Video Material Diffusion for Single Image 3D Generation
  7. 2026Beyond Pixels: From Video Priors to 4D Worlds
  8. 2024V3D: Video Diffusion Models are Effective 3D Generators