mlsanityData to 14 Oct 2026

Learning Formation of Physically-Based Face Attributes

arXiv 2004.03458 ↗First posted 2 Apr 2020cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

Based on a combined data set of 4000 high resolution facial scans, we introduce a non-linear morphable face model, capable of producing multifarious face geometry of pore-level resolution, coupled with material attributes for use in physically-based rendering. We aim to maximize the variety of face identities, while increasing the robustness of correspondence between unique components, including middle-frequency geometry, albedo maps, specular intensity maps and high-frequency displacement details. Our deep learning based generative model learns to correlate albedo and geometry, which ensures the anatomical correctness of the generated assets. We demonstrate potential use of our generative model for novel identity generation, model fitting, interpolation, animation, high fidelity data visualization, and low-to-high resolution data domain transferring. We hope the release of this generative model will encourage further cooperation between all graphics, vision, and data focused professionals while demonstrating the cumulative value of every individual's complete biometric profile.

Key facts. Cited by 94 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 23; 2024: 19; 2025: 20; 2026: 10.

94 papers.

Sort:

By area:

  1. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  2. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  3. 2023Relightable Gaussian Codec Avatarscited by 127
  4. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  5. 2022Learning Neural Parametric Head Modelscited by 73
  6. 2022ClipFace: Text-guided Editing of Textured 3D Morphable Modelscited by 60
  7. 2021AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANscited by 49
  8. 2021Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracingcited by 48
  9. 2024URAvatar: Universal Relightable Gaussian Codec Avatarscited by 43
  10. 2024Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidancecited by 39
  11. 2023FitMe: Deep Photorealistic 3D Morphable Model Avatarscited by 38
  12. 20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
38 more
  1. 2023HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Fieldcited by 37
  2. 2021Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinementcited by 36
  3. 2021Practical Face Reconstruction via Differentiable Ray Tracingcited by 35
  4. 2023Relightify: Relightable 3D Faces from a Single Image via Diffusion Modelscited by 34
  5. 2022Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguationcited by 32
  6. 2023Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wildcited by 25
  7. 2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
  8. 2022SUPR: A Sparse Unified Part-Based Human Representationcited by 21
  9. 2023Generalizable One-shot Neural Head Avatarcited by 21
  10. 2023Learning a 3D Morphable Face Reflectance Model from Low-cost Datacited by 20
  11. 2024VRMM: A Volumetric Relightable Morphable Head Modelcited by 19
  12. 2023RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-consistent Datasetcited by 18
  13. 2023MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shadingcited by 18
  14. 2022Video-driven Neural Physically-based Facial Asset for Productioncited by 17
  15. 2023Single-Shot Implicit Morphable Faces with Consistent Texture Parameterizationcited by 16
  16. 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidancecited by 16
  17. 20213D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Facescited by 15
  18. 202550 Years of Automated Face Recognitioncited by 15
  19. 2024Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusioncited by 12
  20. 2024HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformationcited by 11
  21. 2022BareSkinNet: De-makeup and De-lighting via 3D Face Reconstructioncited by 10
  22. 2021Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Trackingcited by 9
  23. 2021FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networkscited by 9
  24. 2023High-Quality Facial Geometry and Appearance Capture at Homecited by 9
  25. 2022Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearancecited by 8
  26. 2024Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capturecited by 8
  27. 2024Makeup Prior Models for 3D Facial Makeup Estimation and Applicationscited by 7
  28. 2025FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategycited by 7
  29. 2025FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Posescited by 7
  30. 20233D Generative Model Latent Disentanglement via Local Eigenprojectioncited by 6
  31. 2024High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Renderingcited by 6
  32. 2024Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generationcited by 6
  33. 20213D human tongue reconstruction from single "in-the-wild" imagescited by 5
  34. 2023FitDiff: Robust monocular 3D facial shape and reflectance estimation using Diffusion Modelscited by 5
  35. 2023HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMscited by 5
  36. 2024Implicit Neural Representation for Physics-driven Actuated Soft Bodiescited by 5
  37. 2024Monocular Identity-Conditioned Facial Reflectance Reconstructioncited by 5
  38. 2024ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Samplingcited by 5

50 most cited of 94 All 94 (JSON)