mlsanityData to 7 Oct 2026

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video

arXiv 2411.15604 ↗First posted 23 Nov 2024cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

Reconstructing high-fidelity, animatable 3D head avatars from effortlessly captured monocular videos is a pivotal yet formidable challenge. Although significant progress has been made in rendering performance and manipulation capabilities, notable challenges remain, including incomplete reconstruction and inefficient Gaussian representation. To address these challenges, we introduce FATE, a novel method for reconstructing an editable full-head avatar from a single monocular video. FATE integrates a sampling-based densification strategy to ensure optimal positional distribution of points, improving rendering efficiency. A neural baking technique is introduced to convert discrete Gaussian representations into continuous attribute maps, facilitating intuitive appearance editing. Furthermore, we propose a universal completion framework to recover non-frontal appearance, culminating in a 360^circ-renderable 3D head avatar. FATE outperforms previous approaches in both qualitative and quantitative evaluations, achieving state-of-the-art performance. To the best of our knowledge, FATE is the first animatable and 360^circ full-head monocular reconstruction method for a 3D head avatar.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 61 of its 77 references that are in the map. First posted on arXiv 23 Nov 2024.

Builds on

61 of 77 references.

References · 61

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  9. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  10. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  11. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  12. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
38 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  2. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  3. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
  4. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  5. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  6. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  7. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  8. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  9. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 254
  10. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 230
  11. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  12. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  13. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  14. 2023NeRSemble: Multi-view Radiance Field Reconstruction of Human Headscited by 190
  15. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  16. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
  17. 2022Towards Metrical Reconstruction of Human Facescited by 165
  18. 2022Instant Volumetric Head Avatarscited by 157
  19. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  20. 2020MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decompositioncited by 127
  21. 2023Relightable Gaussian Codec Avatarscited by 126
  22. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  23. 2023FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embeddingcited by 107
  24. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  25. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  26. 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
  27. 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
  28. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  29. 20243D Gaussian Blendshapes for Head Avatar Animationcited by 58
  30. 2024GGHead: Fast and Generalizable 3D Gaussian Headscited by 51
  31. 2024URAvatar: Universal Relightable Gaussian Codec Avatarscited by 43
  32. 2023Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesiscited by 37
  33. 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 34
  34. 2023Towards Practical Capture of High-Fidelity Relightable Avatarscited by 34
  35. 2023High-Fidelity 3D Face Generation from Natural Language Descriptionscited by 32
  36. 2021VariTex: Variational Neural Face Texturescited by 30
  37. 2022DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generationcited by 30
  38. 2024SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representationcited by 30

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 15; 2026: 16.

31 papers.

Sort:

By area:

  1. 2025HRAvatar: High-Quality and Relightable Gaussian Head Avatarcited by 24
  2. 2025HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generationcited by 17
  3. 2025SEGA: Drivable 3D Gaussian Head Avatar from a Single Imagecited by 11
  4. 2025FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervisioncited by 10
  5. 2025CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesiscited by 6
  6. 2025TeRA: Rethinking Text-guided Realistic 3D Avatar Generationcited by 5
  7. 2026UIKA: Fast Universal Head Avatar from Pose-Free Imagescited by 5
  8. 2025STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstructioncited by 3
  9. 2025Bringing Your Portrait to 3D Presencecited by 3
  10. 2026EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalizationcited by 3
  11. 2025FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformationcited by 2
  12. 2025Fast Texture Transfer for XR Avatars via Barycentric UV Conversioncited by 1
19 more
  1. 2025AvatarBack: Back-Head Generation for Complete 3D Avatars from Front-View Imagescited by 1
  2. 2025ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatarscited by 1
  3. 2025EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Headcited by 1
  4. 2025GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatarscited by 1
  5. 2026VRGaussianAvatar: Integrating 3D Gaussian Avatars into VRcited by 1
  6. 2026Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generationcited by 1
  7. 2026OmniFaceRig: Fully Automatic Inner-Mouth-Aware Face Rigging Across Diverse 3D Character Topologiescited by 1
  8. 2025Using Gaussian Splats to Create High-Fidelity Facial Geometry and Texturecited by 0
  9. 2026One-Shot Feed-Forward 360circ Animatable Avatar via Inpainted UV-Space Gaussian Modelingcited by 0
  10. 2026OMEGA-Avatar: One-shot Modeling of 360deg Gaussian Avatarscited by 0
  11. 2026FaceCam: Portrait Video Camera Control via Scale-Aware Conditioningcited by 0
  12. 2026DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Videocited by 0
  13. 2026Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatarscited by 0
  14. 2026AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalizationcited by 0
  15. 2026FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibilitycited by 0
  16. 2026FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Headcited by 0
  17. 2026URHead: A Unified UV-Space Representation for Joint Mesh-3DGS Optimization in Head Avatarscited by 0
  18. 2026MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modelingcited by 0
  19. 2026Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responsescited by 0