mlsanityData to 7 Oct 2026

How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)

arXiv 1703.07332 ↗First posted 21 Mar 2017cs.CV cs.LGcited by 524

Not on the map. Why?

Cited by 33 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper investigates how far a very deep neural network is from attaining close to saturating performance on existing 2D and 3D face alignment datasets. To this end, we make the following 5 contributions: (a) we construct, for the first time, a very strong baseline by combining a state-of-the-art architecture for landmark localization with a state-of-the-art residual block, train it on a very large yet synthetically expanded 2D facial landmark dataset and finally evaluate it on all other 2D facial landmark datasets. (b) We create a guided by 2D landmarks network which converts 2D landmark annotations to 3D and unifies all existing datasets, leading to the creation of LS3D-W, the largest and most challenging 3D facial landmark dataset to date ~230,000 images. (c) Following that, we train a neural network for 3D face alignment and evaluate it on the newly introduced LS3D-W. (d) We further look into the effect of all "traditional" factors affecting face alignment performance like large pose, initialization and resolution, and introduce a "new" one, namely the size of the network. (e) We show that both 2D and 3D face alignment networks achieve performance of remarkable accuracy which is probably close to saturating the datasets used. Training and testing code as well as the dataset can be downloaded from https://www.adrianbulat.com/face-alignment/

Key facts. Cited by 524 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 106; 2022: 105; 2023: 110; 2024: 83; 2025: 66; 2026: 54.

524 papers.

Sort:

By area:

  1. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  2. 2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
  3. 2021Motion Representations for Articulated Animationcited by 253
  4. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 230
  5. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  6. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  7. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  8. 2022Thin-Plate Spline Motion Model for Image Animationcited by 209
  9. 2023Controlling Text-to-Image Diffusion by Orthogonal Finetuningcited by 207
  10. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  11. 2022Latent Image Animator: Learning to Animate Images via Latent Space Navigationcited by 172
  12. 2022Towards Metrical Reconstruction of Human Facescited by 165
38 more
  1. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  2. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  3. 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
  4. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  5. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  6. 2022VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wildcited by 106
  7. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  8. 2023Emotional Speech-Driven Animation with Content-Emotion Disentanglementcited by 98
  9. 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesiscited by 97
  10. 2024Generalizable and Animatable Gaussian Head Avatarcited by 95
  11. 2022Visual Speech Recognition for Multiple Languages in the Wildcited by 94
  12. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  13. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  14. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  15. 2022Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decompositioncited by 81
  16. 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 81
  17. 2021KoDF: A Large-scale Korean DeepFake Detection Datasetcited by 80
  18. 2022DiffFace: Diffusion-based Face Swapping with Facial Guidancecited by 77
  19. 2024GPAvatar: Generalizable and Precise Head Avatar from Image(s)cited by 74
  20. 2022GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifoldscited by 73
  21. 20223D face reconstruction with dense landmarkscited by 70
  22. 2023One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Fieldcited by 68
  23. 2021A Latent Transformer for Disentangled Face Editing in Images and Videoscited by 67
  24. 2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
  25. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  26. 2022MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wildcited by 65
  27. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  28. 2023Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generationcited by 61
  29. 2021Privacy-Preserving Portrait Mattingcited by 60
  30. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  31. 2022Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priorscited by 55
  32. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  33. 2024LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervisioncited by 53
  34. 2024CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Modelscited by 52
  35. 2022Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videoscited by 50
  36. 2023Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronizationcited by 49
  37. 2021Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracingcited by 48
  38. 2023Face Animation with an Attribute-Guided Diffusion Modelcited by 48

50 most cited of 524 All 524 (JSON)