mlsanityData to 7 Oct 2026

Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction

arXiv 2012.03065 ↗First posted 5 Dec 2020cs.CV cs.GRcited by 465

Not on the map. Why?

Abstract (arXiv)

We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence applications in AR or VR, a faithful reproduction of the appearance including novel viewpoints or head-poses is required. In contrast to state-of-the-art approaches that model the geometry and material properties explicitly, or are purely image-based, we introduce an implicit representation of the head based on scene representation networks. To handle the dynamics of the face, we combine our scene representation network with a low-dimensional morphable model which provides explicit control over pose and expressions. We use volumetric rendering to generate images from this hybrid representation and demonstrate that such a dynamic neural scene representation can be learned from monocular input data only, without the need of a specialized capture setup. In our experiments, we show that this learned volumetric representation allows for photo-realistic image generation that surpasses the quality of state-of-the-art video-based reenactment methods.

Key facts. Cited by 465 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 49; 2022: 93; 2023: 126; 2024: 83; 2025: 63; 2026: 51.

465 papers.

Sort:

By area:

  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  2. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  3. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  4. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  5. 2021Neural Fields in Visual Computing and Beyondcited by 539
  6. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  7. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  8. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  9. 2021Advances in Neural Renderingcited by 365
  10. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  11. 2021Neural RGB-D Surface Reconstructioncited by 312
  12. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
38 more
  1. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 256
  2. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  3. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
  4. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  5. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  6. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  7. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 230
  8. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  9. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  10. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  11. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  12. 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
  13. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  14. 2023NeRSemble: Multi-view Radiance Field Reconstruction of Human Headscited by 190
  15. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  16. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 171
  17. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
  18. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  19. 2022Instant Volumetric Head Avatarscited by 157
  20. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  21. 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
  22. 2021Real-time Deep Dynamic Characterscited by 133
  23. 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
  24. 2023GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesiscited by 131
  25. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  26. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  27. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  28. 2023GART: Gaussian Articulated Template Modelscited by 121
  29. 2023Drivable 3D Gaussian Avatarscited by 120
  30. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  31. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  32. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  33. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  34. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  35. 2021Light Field Neural Renderingcited by 108
  36. 2023FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embeddingcited by 107
  37. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  38. 2022Generative Neural Articulated Radiance Fieldscited by 101

50 most cited of 465 All 465 (JSON)