mlsanityData to 14 Oct 2026

AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels

arXiv 2211.13206 ↗First posted 23 Nov 2022cs.CVcited by 73

Not on the map. Why?

Abstract (arXiv)

With NeRF widely used for facial reenactment, recent methods can recover photo-realistic 3D head avatar from just a monocular video. Unfortunately, the training process of the NeRF-based methods is quite time-consuming, as MLP used in the NeRF-based methods is inefficient and requires too many iterations to converge. To overcome this problem, we propose AvatarMAV, a fast 3D head avatar reconstruction method using Motion-Aware Neural Voxels. AvatarMAV is the first to model both the canonical appearance and the decoupled expression motion by neural voxels for head avatar. In particular, the motion-aware neural voxels is generated from the weighted concatenation of multiple 4D tensors. The 4D tensors semantically correspond one-to-one with 3DMM expression basis and share the same weights as 3DMM expression coefficients. Benefiting from our novel representation, the proposed AvatarMAV can recover photo-realistic head avatars in just 5 minutes (implemented with pure PyTorch), which is significantly faster than the state-of-the-art facial reenactment methods. Project page: https://www.liuyebin.com/avatarmav.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Builds on 40 of its 66 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

40 of 66 references.

References · 40

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  5. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  8. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  9. 2020First Order Motion Model for Image Animationcited by 704
  10. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 632
  11. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  12. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 444
28 more
  1. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  2. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  3. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 320
  4. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  5. 2018Deep Video Portraitscited by 267
  6. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  7. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  8. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  9. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  10. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 214
  11. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  12. 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
  13. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  14. 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 137
  15. 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
  16. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  17. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  18. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  19. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  20. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  21. 2021FENeRF: Face Editing in Neural Radiance Fieldscited by 112
  22. 2020HeadGAN: One-shot Neural Head Synthesis and Editingcited by 105
  23. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  24. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  25. 2020Head2Head: Video-based Neural Head Synthesiscited by 40
  26. 2021FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animationcited by 33
  27. 2020Head2Head++: Deep Facial Attributes Re-Targetingcited by 30
  28. 2021VariTex: Variational Neural Face Texturescited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 17; 2024: 25; 2025: 19; 2026: 12.

73 papers.

Sort:

By area:

  1. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
  2. 2023FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embeddingcited by 108
  3. 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
  4. 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 84
  5. 2024EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatarscited by 66
  6. 2023HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splattingcited by 60
  7. 20243D Gaussian Blendshapes for Head Avatar Animationcited by 58
  8. 2025Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatarscited by 53
  9. 2023StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Videocited by 52
  10. 2023LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatarcited by 50
  11. 2023GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivationcited by 46
  12. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
38 more
  1. 2024HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priorscited by 44
  2. 2023FLARE: Fast Learning of Animatable and Relightable Mesh Avatarscited by 39
  3. 2024MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editingcited by 38
  4. 2024GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusioncited by 36
  5. 2023HHAvatar: Gaussian Head Avatar with Dynamic Hairscited by 35
  6. 2024HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splattingcited by 35
  7. 2024FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Videocited by 32
  8. 2024GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representationscited by 31
  9. 2025RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatarscited by 29
  10. 2025HRAvatar: High-Quality and Relightable Gaussian Head Avatarcited by 25
  11. 2023VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streamscited by 22
  12. 2024Gaussian Eigen Models for Human Headscited by 21
  13. 2023BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesiscited by 20
  14. 2023InvertAvatar: Incremental GAN Inversion for Generalized Head Avatarscited by 19
  15. 2025InsTaG: Learning Personalized 3D Talking Head from Few-Second Videocited by 18
  16. 2024PSAvatar: A Point-based Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splattingcited by 17
  17. 2024Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fieldscited by 15
  18. 2024SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatarscited by 15
  19. 2025Synthetic Prior for Few-Shot Drivable Head Avatar Inversioncited by 14
  20. 20253D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representationscited by 14
  21. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  22. 2024GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Imagecited by 12
  23. 2025ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressionscited by 12
  24. 2025SEGA: Drivable 3D Gaussian Head Avatar from a Single Imagecited by 11
  25. 2025SOAP: Style-Omniscient Animatable Portraitscited by 11
  26. 2024GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstructioncited by 10
  27. 2025Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusioncited by 9
  28. 2024Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapescited by 8
  29. 2024ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidancecited by 7
  30. 2024High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Renderingcited by 6
  31. 2024SPARK: Self-supervised Personalized Real-time Monocular Face Capturecited by 6
  32. 2023High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Fieldcited by 5
  33. 2024Dynamic NeRF: A Reviewcited by 5
  34. 2025GHOST 2.0: generative high-fidelity one shot transfer of headscited by 5
  35. 2026UIKA: Fast Universal Head Avatar from Pose-Free Imagescited by 5
  36. 2024Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warpingcited by 4
  37. 2024MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussianscited by 4
  38. 2025GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatarcited by 3

50 most cited of 73 All 73 (JSON)