mlsanityData to 14 Oct 2026

FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding

arXiv 2312.02214 ↗First posted 3 Dec 2023cs.CV cs.GRcited by 108

Not on the map. Why?

Abstract (arXiv)

We propose FlashAvatar, a novel and lightweight 3D animatable avatar representation that could reconstruct a digital avatar from a short monocular video sequence in minutes and render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU. To achieve this, we maintain a uniform 3D Gaussian field embedded in the surface of a parametric face model and learn extra spatial offset to model non-surface regions and subtle facial details. While full use of geometric priors can capture high-frequency facial details and preserve exaggerated expressions, proper initialization can help reduce the number of Gaussians, thus enabling super-fast rendering speed. Extensive experimental results demonstrate that FlashAvatar outperforms existing works regarding visual quality and personalized details and is almost an order of magnitude faster in rendering speed. Project page: https://ustc3dv.github.io/FlashAvatar/

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). Builds on 50 of its 64 references that are in the map. First posted on arXiv 3 Dec 2023.

Builds on

50 of 64 references.

References · 50

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  9. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  10. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  11. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  12. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
38 more
  1. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  2. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  3. 2020Neural Sparse Voxel Fieldscited by 959
  4. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  5. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  6. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  7. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  8. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  9. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  10. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  11. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  12. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
  13. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  14. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  15. 2023Text-to-3D using Gaussian Splattingcited by 299
  16. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  17. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  18. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
  19. 2018Deep Video Portraitscited by 267
  20. 2019Neural Voice Puppetry: Audio-driven Facial Reenactmentcited by 250
  21. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  22. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  23. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  24. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  25. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  26. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
  27. 2022Towards Metrical Reconstruction of Human Facescited by 166
  28. 2022Instant Volumetric Head Avatarscited by 159
  29. 2018Nonlinear 3D Face Morphable Modelcited by 157
  30. 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
  31. 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 137
  32. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  33. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  34. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  35. 2022Generative Neural Articulated Radiance Fieldscited by 101
  36. 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
  37. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
  38. 2023HACK: Learning a Parametric Head and Neck Model for High-fidelity Animationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 23; 2025: 35; 2026: 47.

108 papers.

Sort:

By area:

  1. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 78
  2. 2023HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splattingcited by 60
  3. 2025Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatarscited by 53
  4. 2024CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Modelscited by 52
  5. 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
  6. 2024HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priorscited by 44
  7. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 41
  8. 2024MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editingcited by 38
  9. 2023HHAvatar: Gaussian Head Avatar with Dynamic Hairscited by 35
  10. 2024FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Videocited by 32
  11. 2025RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatarscited by 29
  12. 2025HRAvatar: High-Quality and Relightable Gaussian Head Avatarcited by 25
38 more
  1. 2024Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernelscited by 22
  2. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  3. 2024VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresencecited by 19
  4. 2024Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospectscited by 17
  5. 2025MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatarscited by 17
  6. 2024Rig3DGS: Creating Controllable Portraits from Casual Monocular Videoscited by 16
  7. 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidancecited by 16
  8. 2024SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatarscited by 15
  9. 2025Synthetic Prior for Few-Shot Drivable Head Avatar Inversioncited by 14
  10. 20253D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representationscited by 14
  11. 2024GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussianscited by 11
  12. 2025TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splattingcited by 11
  13. 2025SEGA: Drivable 3D Gaussian Head Avatar from a Single Imagecited by 11
  14. 2025SOAP: Style-Omniscient Animatable Portraitscited by 11
  15. 2024GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstructioncited by 10
  16. 2024Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilitiescited by 10
  17. 2025FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervisioncited by 10
  18. 2024GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splattingcited by 9
  19. 2025SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussianscited by 8
  20. 2024SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surfacecited by 7
  21. 2024GASP: Gaussian Avatars with Synthetic Priorscited by 7
  22. 2025RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussianscited by 7
  23. 2025HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatarscited by 7
  24. 2025FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Posescited by 7
  25. 2024High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Renderingcited by 6
  26. 2024GaussianStyle: Gaussian Head Avatar via StyleGANcited by 6
  27. 2025InstaFace: Identity-Preserving Facial Editing with Single Image Inferencecited by 5
  28. 2026UIKA: Fast Universal Head Avatar from Pose-Free Imagescited by 5
  29. 2024SparseLGS: Sparse View Language Embedded Gaussian Splattingcited by 4
  30. 2024MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussianscited by 4
  31. 2025TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modelingcited by 4
  32. 2025GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptationcited by 4
  33. 2025STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstructioncited by 4
  34. 2025Controlling Avatar Diffusion with Learnable Gaussian Embeddingcited by 3
  35. 2025DynaSplat: Dynamic-Static Gaussian Splatting with Hierarchical Motion Decomposition for Scene Reconstructioncited by 3
  36. 2025HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatarscited by 3
  37. 2025VoluMe -- Authentic 3D Video Calls from Live Gaussian Splat Predictioncited by 3
  38. 2025Bringing Your Portrait to 3D Presencecited by 3

50 most cited of 108 All 108 (JSON)