mlsanityData to 7 Oct 2026

Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

arXiv 2011.13084 ↗First posted 26 Nov 2020cs.CVcited by 750

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a method to perform novel view and time synthesis of dynamic scenes, requiring only a monocular video with known camera poses as input. To do this, we introduce Neural Scene Flow Fields, a new representation that models the dynamic scene as a time-variant continuous function of appearance, geometry, and 3D scene motion. Our representation is optimized through a neural network to fit the observed input views. We show that our representation can be used for complex dynamic scenes, including thin structures, view-dependent effects, and natural degrees of motion. We conduct a number of experiments that demonstrate our approach significantly outperforms recent monocular view synthesis methods, and show qualitative results of space-time view synthesis on a variety of real-world videos.

Key facts. Cited by 750 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 78; 2022: 136; 2023: 184; 2024: 172; 2025: 110; 2026: 70.

750 papers.

Sort:

By area:

  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  4. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  5. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  7. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  8. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  10. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  11. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  12. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
38 more
  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  3. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  4. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  5. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  6. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  7. 2021Advances in Neural Renderingcited by 365
  8. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  9. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  10. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  11. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  12. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  13. 2021Neural RGB-D Surface Reconstructioncited by 312
  14. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  15. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  16. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  17. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  18. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  19. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  20. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  21. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  22. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  23. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  24. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 228
  25. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  26. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  27. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
  28. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  29. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  30. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  31. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  32. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 210
  33. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204
  34. 2023Text-To-4D Dynamic Scene Generationcited by 204
  35. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  36. 2021Neural Articulated Radiance Fieldcited by 196
  37. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  38. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195

50 most cited of 750 All 750 (JSON)