mlsanityData to 14 Oct 2026

Neural Trajectory Fields for Dynamic Novel View Synthesis

arXiv 2105.05994 ↗First posted 12 May 2021cs.CVcited by 86

Not on the map. Why?

Abstract (arXiv)

Recent approaches to render photorealistic views from a limited set of photographs have pushed the boundaries of our interactions with pictures of static scenes. The ability to recreate moments, that is, time-varying sequences, is perhaps an even more interesting scenario, but it remains largely unsolved. We introduce DCT-NeRF, a coordinatebased neural representation for dynamic scenes. DCTNeRF learns smooth and stable trajectories over the input sequence for each point in space. This allows us to enforce consistency between any two frames in the sequence, which results in high quality reconstruction, particularly in dynamic regions.

Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 12 May 2021.

Builds on

34 of 54 references.

References · 34

  1. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  10. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  11. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  12. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
22 more
  1. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  2. 2020State of the Art on Neural Renderingcited by 278
  3. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  4. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  5. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  6. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  7. 2020Consistent Video Depth Estimationcited by 220
  8. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  9. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  10. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  11. 2020Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Cameracited by 166
  12. 2020Stable View Synthesiscited by 165
  13. 2020DeRF: Decomposed Radiance Fieldscited by 163
  14. 2016Learning-Based View Synthesis for Light Field Camerascited by 145
  15. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  16. 2018Extreme View Synthesiscited by 94
  17. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  18. 2020Portrait Neural Radiance Fields from a Single Imagecited by 61
  19. 2017Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Framescited by 27
  20. 2020Semantic View Synthesiscited by 18
  21. 2018A Benchmark and Evaluation of Non-Rigid Structure from Motioncited by 14
  22. 2020Generative View Synthesis: From Single-view Semantics to Novel-view Imagescited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 22; 2024: 30; 2025: 18; 2026: 6.

86 papers.

Sort:

By area:

  1. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  2. 2021Neural Fields in Visual Computing and Beyondcited by 540
  3. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  4. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  5. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  6. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  7. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 197
  8. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 179
  9. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 152
  10. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  11. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117
  12. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
38 more
  1. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
  2. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  3. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  4. 2023Forward Flow for Novel View Synthesis of Dynamic Scenescited by 68
  5. 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Modelscited by 64
  6. 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 63
  7. 2024SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstructioncited by 52
  8. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  9. 2023EPIC Fields: Marrying 3D Geometry and Video Understandingcited by 49
  10. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 44
  11. 2022Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesiscited by 43
  12. 2024Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modelingcited by 43
  13. 2023Flow supervision for Deformable NeRFcited by 42
  14. 2023DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulationcited by 42
  15. 2023DynPoint: Dynamic Neural Point For View Synthesiscited by 37
  16. 20244D Gaussian Splatting with Scale-aware Residual Field and Adaptive Optimization for Real-time Rendering of Temporally Complex Dynamic Scenescited by 37
  17. 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splattingcited by 36
  18. 2025Trace Anything: Representing Any Video in 4D via Trajectory Fieldscited by 33
  19. 2023Control4D: Efficient 4D Portrait Editing with Textcited by 32
  20. 2024Splatter a Video: Video Gaussian Representation for Versatile Processingcited by 31
  21. 2021HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capturecited by 29
  22. 2023NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videoscited by 28
  23. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  24. 2023ResFields: Residual Neural Fields for Spatiotemporal Signalscited by 27
  25. 2024QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videoscited by 25
  26. 2024Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimationcited by 24
  27. 2023Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesiscited by 20
  28. 2024CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Videocited by 18
  29. 2024Diffusion Priors for Dynamic View Synthesis from Monocular Videoscited by 18
  30. 2023Decoupling Dynamic Monocular Videos for Dynamic View Synthesiscited by 17
  31. 2024DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Videocited by 17
  32. 2023Event-based Continuous Color Video Decompression from Single Framescited by 15
  33. 20244Dynamic: Text-to-4D Generation with Hybrid Priorscited by 15
  34. 2025DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videoscited by 15
  35. 20253D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representationscited by 14
  36. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  37. 2022PREF: Predictability Regularized Neural Motion Fieldscited by 13
  38. 2022Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Cameracited by 12

50 most cited of 86 All 86 (JSON)