mlsanityData to 7 Oct 2026

3D face reconstruction with dense landmarks

arXiv 2204.02776 ↗First posted 6 Apr 2022cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

Landmarks often play a key role in face analysis, but many aspects of identity or expression cannot be represented by sparse landmarks alone. Thus, in order to reconstruct faces more accurately, landmarks are often combined with additional signals like depth images or techniques like differentiable rendering. Can we keep things simple by just using more landmarks? In answer, we present the first method that accurately predicts 10x as many landmarks as usual, covering the whole head, including the eyes and teeth. This is accomplished using synthetic training data, which guarantees perfect landmark annotations. By fitting a morphable model to these dense landmarks, we achieve state-of-the-art results for monocular 3D face reconstruction in the wild. We show that dense landmarks are an ideal signal for integrating face shape information across frames by demonstrating accurate and expressive facial performance capture in both monocular and multi-view scenarios. This approach is also highly efficient: we can predict dense landmarks and fit our 3D face model at over 150FPS on a single CPU thread. Please see our website: https://microsoft.github.io/DenseLandmarks/.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). Builds on 45 of its 78 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

45 of 78 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  7. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  8. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  9. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
  10. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  11. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  12. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
33 more
  1. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  2. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  3. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  4. 2018Nonlinear 3D Face Morphable Modelcited by 157
  5. 2017Morphable Face Models - An Open Frameworkcited by 138
  6. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 137
  7. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 127
  8. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  9. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 99
  10. 2017Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hzcited by 91
  11. 2019Towards High-fidelity Nonlinear 3D Face Morphable Modelcited by 91
  12. 2020LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihoodcited by 87
  13. 2018FML: Face Model Learning from Videoscited by 78
  14. 2020Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistencycited by 78
  15. 2019Real-time Facial Surface Geometry from Monocular Video on Mobile GPUscited by 72
  16. 2016Learning Detailed Face Reconstruction from a Single Imagecited by 71
  17. 20163D Face Reconstruction by Learning from Synthetic Datacited by 64
  18. 2017Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translationcited by 56
  19. 2021Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracingcited by 48
  20. 2017End-to-end 3D face reconstruction with deep neural networkscited by 47
  21. 2021Practical Face Reconstruction via Differentiable Ray Tracingcited by 35
  22. 2014Effective Face Frontalization in Unconstrained Imagescited by 34
  23. 20193FabRec: Fast Few-shot Face alignment by Reconstructioncited by 33
  24. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  25. 2021Riggable 3D Face Reconstruction via In-Network Optimizationcited by 31
  26. 2020Attention Mesh: High-fidelity Face Mesh Prediction in Real-timecited by 30
  27. 2018Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognitioncited by 27
  28. 2017Dense Face Alignmentcited by 24
  29. 2020Survey on 3D face reconstruction from uncalibrated imagescited by 24
  30. 2019Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoderscited by 22
  31. 2021Subpixel Heatmap Regression for Facial Landmark Localizationcited by 14
  32. 2019Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Trackingcited by 12
  33. 2019Local Geometric Indexing of High Resolution Data for Facial Reconstruction from Sparse Markerscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 23; 2024: 16; 2025: 13; 2026: 11.

70 papers.

Sort:

By area:

  1. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  2. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  3. 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 81
  4. 2022MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptationcited by 69
  5. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
  6. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  7. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  8. 2023STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detectioncited by 41
  9. 2022VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representationscited by 36
  10. 2023Instant Multi-View Head Capture through Learnable Registrationcited by 34
  11. 2024FaceXFormer: A Unified Transformer for Facial Analysiscited by 34
  12. 2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
38 more
  1. 2023DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 20
  2. 20243D Face Tracking from 2D Video through Iterative Dense UV to Image Flowcited by 20
  3. 2025Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstructioncited by 20
  4. 2024SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Camerascited by 12
  5. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
  6. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  7. 2023Text-Guided 3D Face Synthesis -- From Generation to Editingcited by 8
  8. 2023Make-A-Character: High Quality Text-to-3D Character Generation within Minutescited by 8
  9. 2024Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capturecited by 8
  10. 2025SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussianscited by 8
  11. 2024T-FAKE: Synthesizing Thermal Images for Facial Landmarkingcited by 7
  12. 2023Few-shot Geometry-Aware Keypoint Localizationcited by 6
  13. 2023ASM: Adaptive Skinning Model for High-Quality 3D Face Modelingcited by 6
  14. 2023BlendFields: Few-Shot Example-Driven Facial Modelingcited by 6
  15. 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignmentcited by 6
  16. 2023A Perceptual Shape Loss for Monocular 3D Face Reconstructioncited by 6
  17. 2024SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimationcited by 6
  18. 2024VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstructioncited by 6
  19. 2022Mesh-Tension Driven Expression-Based Wrinkles for Synthetic Facescited by 5
  20. 2023A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimizationcited by 5
  21. 2023FitDiff: Robust monocular 3D facial shape and reflectance estimation using Diffusion Modelscited by 5
  22. 2022Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regressioncited by 4
  23. 2023Procedural Humans for Computer Visioncited by 4
  24. 2024SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargetingcited by 4
  25. 2023Disjoint Pose and Shape for 3D Face Reconstructioncited by 3
  26. 2024Text-based Talking Video Editing with Cascaded Conditional Diffusioncited by 3
  27. 2024FaceLift: Semi-supervised 3D Facial Landmark Localizationcited by 2
  28. 2024Infinite 3D Landmarks: Improving Continuous 2D Facial Landmark Detectioncited by 2
  29. 2025Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunitiescited by 2
  30. 2025High-Quality Facial Albedo Generation for 3D Face Reconstruction from a Single Image using a Coarse-to-Fine Approachcited by 2
  31. 2025Bitrate-Controlled Diffusion for Disentangling Motion and Content in Videocited by 2
  32. 2023A lightweight 3D dense facial landmark estimation model from position map datacited by 1
  33. 2024FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidancecited by 1
  34. 2024Learning Online Scale Transformation for Talking Head Video Generationcited by 1
  35. 2025Learning Semantic Facial Descriptors for Accurate Face Animationcited by 1
  36. 2025Heatmap Regression without Soft-Argmax for Facial Landmark Detectioncited by 1
  37. 2025Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Imagecited by 1
  38. 2026LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelinescited by 1

50 most cited of 70 All 70 (JSON)