mlsanityData to 7 Oct 2026

Neural Scene Graphs for Dynamic Scenes

arXiv 2011.10379 ↗First posted 20 Nov 2020cs.CV cs.GRcited by 298

Not on the map. Why?

Cited by 23 in End-to-end autonomous driving, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent implicit neural rendering methods have demonstrated that it is possible to learn accurate view synthesis for complex scenes by predicting their volumetric density and color supervised solely by a set of RGB images. However, existing methods are restricted to learning efficient representations of static scenes that encode all scene objects into a single neural network, and lack the ability to represent dynamic scenes and decompositions into individual scene objects. In this work, we present the first neural rendering method that decomposes dynamic scenes into scene graphs. We propose a learned scene graph representation, which encodes object transformation and radiance, to efficiently render novel arrangements and views of the scene. To this end, we learn implicitly encoded scenes, combined with a jointly learned latent representation to describe objects with a single implicit function. We assess the proposed method on synthetic and real automotive data, validating that our approach learns dynamic scenes -- only by observing a video of this scene -- and allows for rendering novel photo-realistic views of novel scene compositions with unseen sets of objects at unseen poses.

Key facts. Cited by 298 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 48; 2023: 66; 2024: 82; 2025: 57; 2026: 24.

298 papers.

Sort:

By area:

  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  2. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  3. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  4. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  5. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  6. 2021Neural Fields in Visual Computing and Beyondcited by 539
  7. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
  8. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  9. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 387
  10. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  11. 2021Advances in Neural Renderingcited by 365
  12. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
38 more
  1. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  2. 2021Urban Radiance Fieldscited by 263
  3. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  4. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  5. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  6. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  7. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  8. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  9. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  10. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  11. 2023MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Drivingcited by 170
  12. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  13. 2024OmniRe: Omni Urban Scene Reconstructioncited by 159
  14. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  15. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
  16. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  17. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  18. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 146
  19. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  20. 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splattingcited by 141
  21. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  22. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  23. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  24. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representationcited by 123
  25. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  26. 20213D Neural Scene Representations for Visuomotor Controlcited by 110
  27. 2024textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Drivingcited by 105
  28. 2021Unsupervised Discovery of Object Radiance Fieldscited by 100
  29. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 99
  30. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  31. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  32. 2024ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restorationcited by 89
  33. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  34. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
  35. 2022Deforming Radiance Fields with Cagescited by 78
  36. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  37. 2021Learning to Stylize Novel Viewscited by 76
  38. 2022Object-Compositional Neural Implicit Surfacescited by 74

50 most cited of 298 All 298 (JSON)