mlsanityData to 7 Oct 2026

4D Visualization of Dynamic Events from Unconstrained Multi-View Videos

arXiv 2005.13532 ↗First posted 27 May 2020cs.CV cs.GRcited by 66

Not on the map. Why?

Abstract (arXiv)

We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras. Key to our approach is the use of self-supervised neural networks specific to the scene to compose static and dynamic aspects of an event. Though captured from discrete viewpoints, this model enables us to move around the space-time of the event continuously. This model allows us to create virtual cameras that facilitate: (1) freezing the time and exploring views; (2) freezing a view and moving through time; and (3) simultaneously changing both time and view. We can also edit the videos and reveal occluded objects for a given view if it is visible in any of the other views. We validate our approach on challenging in-the-wild events captured using up to 15 mobile cameras.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 7; 2023: 17; 2024: 12; 2025: 12; 2026: 7.

66 papers.

Sort:

By area:

  1. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  2. 2021Advances in Neural Renderingcited by 365
  3. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  4. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  5. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  6. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  7. 2023Robust Dynamic Radiance Fieldscited by 193
  8. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  9. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
  10. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
  11. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  12. 2022Mixed Neural Voxels for Fast Multi-view Video Synthesiscited by 126
38 more
  1. 2022Streaming Radiance Fields for 3D Video Synthesiscited by 118
  2. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 116
  3. 2022DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenescited by 103
  4. 2024ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuningcited by 68
  5. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
  6. 2021Consistent Depth of Moving Objects in Videocited by 56
  7. 2023Representing Volumetric Videos as Dynamic MLP Mapscited by 51
  8. 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
  9. 2024GFlow: Recovering 4D World from Monocular Videocited by 46
  10. 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstructioncited by 43
  11. 2024Vivid-ZOO: Multi-View Video Generation with Diffusion Modelcited by 40
  12. 2024Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfelscited by 38
  13. 2025GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Trackingcited by 37
  14. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  15. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 31
  16. 2023Pseudo-Generalized Dynamic View Synthesis from a Videocited by 27
  17. 2024GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesiscited by 25
  18. 20233D Cinemagraphy from a Single Imagecited by 23
  19. 2023Fast View Synthesis of Casual Videos with Soup-of-Planescited by 22
  20. 2025FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Videocited by 21
  21. 2024CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Videocited by 18
  22. 20223D Moments from Near-Duplicate Photoscited by 15
  23. 2023Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Videocited by 12
  24. 2025LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decouplingcited by 12
  25. 2021Free-Viewpoint RGB-D Human Performance Capture and Renderingcited by 11
  26. 2023SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenescited by 11
  27. 2024DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstructioncited by 10
  28. 2024Modeling Ambient Scene Dynamics for Free-view Synthesiscited by 9
  29. 2022Neural Pixel Composition: 3D-4D View Synthesis from Multi-Viewscited by 7
  30. 2025HoliGS: Holistic Gaussian Splatting for Embodied View Synthesiscited by 7
  31. 2023Replay: Multi-modal Multi-view Acted Videos for Casual Holographycited by 6
  32. 2026Vision Pretraining for Dense Spatial Perceptioncited by 6
  33. 2025Video4DGen: Enhancing Video and 4D Generation through Mutual Optimizationcited by 5
  34. 2025Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Videocited by 5
  35. 20233D Video Loops from Asynchronous Inputcited by 4
  36. 2021View Synthesis of Dynamic Scenes based on Deep 3D Mask Volumecited by 3
  37. 2023Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fieldscited by 3
  38. 2023Virtual Pets: Animatable Animal Generation in 3D Scenescited by 3

50 most cited of 66 All 66 (JSON)