mlsanityData to 7 Oct 2026

Unsupervised Training for 3D Morphable Model Regression

arXiv 1806.06098 ↗First posted 15 Jun 2018cs.CVcited by 99

Not on the map. Why?

Abstract (arXiv)

We present a method for training a regression network from image pixels to 3D morphable model coordinates using only unlabeled photographs. The training loss is based on features from a facial recognition network, computed on-the-fly by rendering the predicted faces with a differentiable renderer. To make training from features feasible and avoid network fooling effects, we introduce three objectives: a batch distribution loss that encourages the output distribution to match the distribution of the morphable model, a loopback loss that ensures the network can correctly reinterpret its own output, and a multi-view identity loss that compares the features of the predicted 3D face and the input photograph from multiple viewing angles. We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 22; 2023: 25; 2024: 7; 2025: 11; 2026: 2.

99 papers.

Sort:

By area:

  1. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  2. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 254
  3. 2022Towards Metrical Reconstruction of Human Facescited by 165
  4. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2023Emotional Speech-Driven Animation with Content-Emotion Disentanglementcited by 98
  7. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  8. 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 81
  9. 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
  10. 20223D face reconstruction with dense landmarkscited by 70
  11. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  12. 2021AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANscited by 49
38 more
  1. 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpaintingcited by 48
  2. 2022Face Relighting with Geometrically Consistent Shadowscited by 43
  3. 2023A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Imagescited by 43
  4. 2021Towards High Fidelity Face Relighting with Realistic Shadowscited by 42
  5. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  6. 2023FitMe: Deep Photorealistic 3D Morphable Model Avatarscited by 38
  7. 20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
  8. 2021Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinementcited by 36
  9. 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 34
  10. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  11. 2023Relightify: Relightable 3D Faces from a Single Image via Diffusion Modelscited by 34
  12. 2023Instant Multi-View Head Capture through Learnable Registrationcited by 34
  13. 2021Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstructioncited by 33
  14. 2022REALY: Rethinking the Evaluation of 3D Face Reconstructioncited by 32
  15. 2022Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguationcited by 32
  16. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 32
  17. 2021Riggable 3D Face Reconstruction via In-Network Optimizationcited by 31
  18. 2021SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstructioncited by 27
  19. 2022Facial Geometric Detail Recovery via Implicit Representationcited by 27
  20. 2021Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderingscited by 23
  21. 20223DFaceShop: Explicitly Controllable 3D-Aware Portrait Generationcited by 22
  22. 2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
  23. 2021Robust Model-based Face Reconstruction through Weakly-Supervised Outlier Segmentationcited by 20
  24. 2023Learning a 3D Morphable Face Reflectance Model from Low-cost Datacited by 20
  25. 2021Cross-Domain and Disentangled Face Manipulation with 3D Guidancecited by 17
  26. 2021Inverting Generative Adversarial Renderer for Face Reconstructioncited by 17
  27. 2021SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Renderingcited by 17
  28. 2021Self-Supervised 3D Face Reconstruction via Conditional Estimationcited by 17
  29. 20223D-FM GAN: Towards 3D-Controllable Face Manipulationcited by 17
  30. 2023Interactive Face Video Coding: A Generative Compression Frameworkcited by 17
  31. 2021MeInGame: Create a Game Character Face from a Single Portraitcited by 16
  32. 2021Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collectioncited by 16
  33. 2022Neural Parameterization for Dynamic Human Head Editingcited by 16
  34. 2023Single-Shot Implicit Morphable Faces with Consistent Texture Parameterizationcited by 16
  35. 2023PAPR: Proximity Attention Point Renderingcited by 16
  36. 2023DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadowscited by 14
  37. 2023Learning Audio-Driven Viseme Dynamics for 3D Face Animationcited by 12
  38. 20223DMM-RF: Convolutional Radiance Fields for 3D Face Modelingcited by 10

50 most cited of 99 All 99 (JSON)