mlsanityData to 7 Oct 2026

Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities

arXiv 2409.16147 ↗First posted 23 Sep 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Recent advancements in 3D Gaussian Splatting (3DGS) have unlocked significant potential for modeling 3D head avatars, providing greater flexibility than mesh-based methods and more efficient rendering compared to NeRF-based approaches. Despite these advancements, the creation of controllable 3DGS-based head avatars remains time-intensive, often requiring tens of minutes to hours. To expedite this process, we here introduce the "Gaussian Deja-vu" framework, which first obtains a generalized model of the head avatar and then personalizes the result. The generalized model is trained on large 2D (synthetic and real) image datasets. This model provides a well-initialized 3D Gaussian head that is further refined using a monocular video to achieve the personalized head avatar. For personalizing, we propose learnable expression-aware rectification blendmaps to correct the initial 3D Gaussians, ensuring rapid convergence without the reliance on neural networks. Experiments demonstrate that the proposed method meets its objectives. It outperforms state-of-the-art 3D Gaussian head avatars in terms of photorealistic quality as well as reduces training time consumption to at least a quarter of the existing methods, producing the avatar in minutes.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 43 of its 67 references that are in the map. First posted on arXiv 23 Sep 2024.

Builds on

43 of 67 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  10. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  11. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
  12. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
31 more
  1. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  2. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  3. 20193D Morphable Face Models -- Past, Present and Futurecited by 269
  4. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  5. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  6. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  7. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  8. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
  9. 2023Relightable Gaussian Codec Avatarscited by 126
  10. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  11. 2023FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embeddingcited by 107
  12. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  13. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  14. 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
  15. 2024GPAvatar: Generalizable and Precise Head Avatar from Image(s)cited by 74
  16. 2023OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Renderingcited by 67
  17. 2023HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splattingcited by 60
  18. 20243D Gaussian Blendshapes for Head Avatar Animationcited by 58
  19. 2020Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networkscited by 51
  20. 2024NPGA: Neural Parametric Gaussian Avatarscited by 46
  21. 2023OmniAvatar: Geometry-Guided Controllable 3D Head Synthesiscited by 34
  22. 2023Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editingcited by 22
  23. 2023GAN-Avatar: Controllable Personalized GAN-based Human Head Avatarcited by 14
  24. 2024Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networkscited by 14
  25. 2024GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Imagecited by 12
  26. 20223DMM-RF: Convolutional Radiance Fields for 3D Face Modelingcited by 10
  27. 2024Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapescited by 8
  28. 2024SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surfacecited by 7
  29. 2024MI-NeRF: Learning a Single Face NeRF from Multiple Identitiescited by 3
  30. 2024G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Imagescited by 3
  31. 2024GGAvatar: Geometric Adjustment of Gaussian Head Avatarcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2024SqueezeMe: Mobile-Ready Distillation of Gaussian Full-Body Avatarscited by 10
  2. 2025FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Posescited by 7
  3. 2025AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatarscited by 3
  4. 2025StyleMorpheus: A Style-Based 3D-Aware Morphable Face Modelcited by 1
  5. 2025ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatarscited by 1
  6. 2026Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generationcited by 1
  7. 2025PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Trackingcited by 0
  8. 2026Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photocited by 0
  9. 2026Learning Semantic Inpainting for Animatable Gaussian Head Avatarscited by 0
  10. 2026One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatarscited by 0