mlsanityData to 7 Oct 2026

Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Video

arXiv 2310.09647 ↗First posted 14 Oct 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Dynamic radiance fields have emerged as a promising approach for generating novel views from a monocular video. However, previous methods enforce the geometric consistency to dynamic radiance fields only between adjacent input frames, making it difficult to represent the global scene geometry and degenerates at the viewpoint that is spatio-temporally distant from the input camera trajectory. To solve this problem, we introduce point-based dynamic radiance fields (Point-DynRF), a novel framework where the global geometric information and the volume rendering process are trained by neural point clouds and dynamic radiance fields, respectively. Specifically, we reconstruct neural point clouds directly from geometric proxies and optimize both radiance fields and the geometric proxies using our proposed losses, allowing them to complement each other. We validate the effectiveness of our method with experiments on the NVIDIA Dynamic Scenes Dataset and several causally captured monocular video clips.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

37 of 51 references.

References · 37

  1. 2017Mask R-CNNcited by 7,259
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  10. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  11. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  12. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
25 more
  1. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  2. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  3. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  4. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  5. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  6. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  7. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  8. 2019Neural Point-Based Graphicscited by 326
  9. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  10. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  11. 2021Editing Conditional Radiance Fieldscited by 222
  12. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  13. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 215
  14. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  15. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  16. 2023Robust Dynamic Radiance Fieldscited by 193
  17. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  18. 2020Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Cameracited by 166
  19. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  20. 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 121
  21. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  22. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  23. 2022AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fieldscited by 68
  24. 20204D Visualization of Dynamic Events from Unconstrained Multi-View Videoscited by 66
  25. 2020MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Imagescited by 64

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 4; 2026: 1.

12 papers.

  1. 2024Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstructioncited by 43
  2. 2024Dynamic 3D Gaussian Fields for Urban Areascited by 35
  3. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesiscited by 34
  4. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  5. 2024Multi-Level Neural Scene Graphs for Dynamic Urban Environmentscited by 27
  6. 2025SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steeringcited by 13
  7. 2025ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encodingcited by 10
  8. 2025Dynamic Scene Reconstruction: Recent Advance in Real-time Rendering and Streamingcited by 8
  9. 2024Gaussians on their Way: Wasserstein-Constrained 4D Gaussian Splatting with State-Space Modelingcited by 1
  10. 2025DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splattingcited by 1
  11. 2024OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videoscited by 0
  12. 2026Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenescited by 0