mlsanityData to 7 Oct 2026

Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streaming

arXiv 2503.08166 ↗First posted 11 Mar 2025cs.GR cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Representing and rendering dynamic scenes from 2D images is a fundamental yet challenging problem in computer vision and graphics. This survey provides a comprehensive review of the evolution and advancements in dynamic scene representation and rendering, with a particular emphasis on recent progress in Neural Radiance Fields based and 3D Gaussian Splatting based reconstruction methods. We systematically summarize existing approaches, categorize them according to their core principles, compile relevant datasets, compare the performance of various methods on these benchmarks, and explore the challenges and future research directions in this rapidly evolving field. In total, we review over 170 relevant papers, offering a broad perspective on the state of the art in this domain.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 99 of its 164 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

99 of 164 references.

References · 99

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2018SlowFast Networks for Video Recognitioncited by 1,862
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  10. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  11. 2018On the Spectral Bias of Neural Networkscited by 1,321
  12. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
38 more
  1. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  2. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  3. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  4. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  5. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  6. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  7. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  8. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  9. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  10. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  11. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
  12. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  13. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  14. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  15. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  16. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  17. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  18. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  19. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  20. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  21. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  22. 2024A Survey on 3D Gaussian Splattingcited by 221
  23. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  24. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 215
  25. 2024Global Structure-from-Motion Revisitedcited by 215
  26. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  27. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 210
  28. 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 185
  29. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  30. 2018Deep Appearance Models for Face Renderingcited by 164
  31. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  32. 2023HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motioncited by 161
  33. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  34. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
  35. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  36. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  37. 2022Streaming Radiance Fields for 3D Video Synthesiscited by 118
  38. 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 110

50 most cited of 99 All 99 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videoscited by 8
  2. 2025UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splattingcited by 2
  3. 2025Consistent Instance Field for Dynamic Scene Understandingcited by 2
  4. 2026MoCam: Unified Novel View Synthesis via Structured Denoising Dynamicscited by 2
  5. 2025Adaptive 3D Gaussian Splatting Video Streaming: Visual Saliency-Aware Tiling and Meta-Learning-Based Bitrate Adaptationcited by 1
  6. 2026Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequencescited by 1
  7. 2026RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splattingcited by 0
  8. 2026Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstructioncited by 0