mlsanityData to 7 Oct 2026

SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

arXiv 2106.03021 ↗First posted 6 Jun 2021cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Three-dimensional face dense alignment and reconstruction in the wild is a challenging problem as partial facial information is commonly missing in occluded and large pose face images. Large head pose variations also increase the solution space and make the modeling more difficult. Our key idea is to model occlusion and pose to decompose this challenging task into several relatively more manageable subtasks. To this end, we propose an end-to-end framework, termed as Self-aligned Dual face Regression Network (SADRNet), which predicts a pose-dependent face, a pose-independent face. They are combined by an occlusion-aware self-alignment to generate the final 3D face. Extensive experiments on two popular benchmarks, AFLW2000-3D and Florence, demonstrate that the proposed method achieves significant superior performance over existing state-of-the-art methods.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 40 of its 75 references that are in the map. First posted on arXiv 6 Jun 2021.

Builds on

40 of 75 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  4. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  5. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
  6. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  7. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  8. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  9. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  10. 2018Nonlinear 3D Face Morphable Modelcited by 157
  11. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  12. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
28 more
  1. 2017Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networkscited by 108
  2. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 99
  3. 2019Towards High-fidelity Nonlinear 3D Face Morphable Modelcited by 91
  4. 2020AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"cited by 91
  5. 2018FML: Face Model Learning from Videoscited by 78
  6. 2020Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistencycited by 78
  7. 2017Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regressioncited by 66
  8. 2017Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translationcited by 56
  9. 2018On Learning 3D Face Morphable Model from In-the-wild Imagescited by 54
  10. 2020Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networkscited by 51
  11. 2019Disentangled Representation Learning for 3D Face Shapecited by 48
  12. 2019MVF-Net: Multi-View 3D Face Morphable Model Regressioncited by 45
  13. 2015Going Deeper in Facial Expression Recognition using Deep Neural Networkscited by 43
  14. 2019Photo-Realistic Facial Details Synthesis from Single Imagecited by 40
  15. 2018Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognitioncited by 27
  16. 2017Dense Face Alignmentcited by 24
  17. 2019Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoderscited by 22
  18. 2017Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognitioncited by 21
  19. 2019Self-supervised Learning of Detailed 3D Face Reconstructioncited by 21
  20. 2017Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Posescited by 19
  21. 2016Production-Level Facial Performance Capture Using Deep Convolutional Neural Networkscited by 14
  22. 2019Facial Pose Estimation by Deep Learning from Label Distributionscited by 10
  23. 2016A Recurrent Encoder-Decoder Network for Sequential Face Alignmentcited by 9
  24. 2016Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challengecited by 8
  25. 2015Fitting 3D Morphable Models using Local Featurescited by 6
  26. 2018Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localizationcited by 6
  27. 2019Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignmentcited by 6
  28. 2018Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 7; 2024: 9; 2025: 5; 2026: 2.

27 papers.

Sort:

  1. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 254
  2. 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 81
  3. 2023A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Imagescited by 43
  4. 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 34
  5. 2022DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Imagecited by 31
  6. 2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
  7. 20243D Face Tracking from 2D Video through Iterative Dense UV to Image Flowcited by 20
  8. 2025TEASER: Token Enhanced Spatial Modeling for Expressions Reconstructioncited by 13
  9. 2025SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussianscited by 8
  10. 2023RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairscited by 6
  11. 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignmentcited by 6
  12. 2024SPARK: Self-supervised Personalized Real-time Monocular Face Capturecited by 6
15 more
  1. 2023FLAME-based Multi-View 3D Face Reconstructioncited by 3
  2. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  3. 2024FaceLift: Semi-supervised 3D Facial Landmark Localizationcited by 2
  4. 2025High-Quality Facial Albedo Generation for 3D Face Reconstruction from a Single Image using a Coarse-to-Fine Approachcited by 2
  5. 2022BabyNet: Reconstructing 3D faces of babies from uncalibrated photographscited by 1
  6. 2023A lightweight 3D dense facial landmark estimation model from position map datacited by 1
  7. 2024CSANet: Channel Spatial Attention Network for Robust 3D Face Alignment and Reconstructioncited by 1
  8. 2026Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondencecited by 1
  9. 20233D Face Alignment Through Fusion of Head Pose Information and Featurescited by 0
  10. 2024Robust 3D Face Alignment with Multi-Path Neural Architecture Searchcited by 0
  11. 2024On the power of data augmentation for head pose estimationcited by 0
  12. 2024OFER: Occluded Face Expression Reconstructioncited by 0
  13. 2025Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Imagescited by 0
  14. 2025GLVD: Guided Learned Vertex Descentcited by 0
  15. 2026RealDenseFace: Real-time Monocular 3D Face Reconstruction from Dense UV-space Priorscited by 0