mlsanityData to 7 Oct 2026

3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs

arXiv 2203.04643 ↗First posted 9 Mar 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel multi-level aggregation network to regress the coordinates of the vertices of a 3D face from a single 2D image in an end-to-end manner. This is achieved by seamlessly combining standard convolutional neural networks (CNNs) with Graph Convolution Networks (GCNs). By iteratively and hierarchically fusing the features across different layers and stages of the CNNs and GCNs, our approach can provide a dense face alignment and 3D face reconstruction simultaneously for the benefit of direct feature learning of 3D face mesh. Experiments on several challenging datasets demonstrate that our method outperforms state-of-the-art approaches on both 2D and 3D face alignment tasks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 9 Mar 2022.

Builds on

39 of 61 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015Fast R-CNNcited by 2,930
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  10. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  11. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  12. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
27 more
  1. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  2. 2017Deep Layer Aggregationcited by 436
  3. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  4. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  5. 2018Nonlinear 3D Face Morphable Modelcited by 157
  6. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  7. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  8. 2017Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networkscited by 108
  9. 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
  10. 2016Learning Detailed Face Reconstruction from a Single Imagecited by 71
  11. 2017Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regressioncited by 66
  12. 20163D Face Reconstruction by Learning from Synthetic Datacited by 64
  13. 2017UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognitioncited by 62
  14. 2017Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translationcited by 56
  15. 20173D Face Morphable Models "In-the-Wild"cited by 44
  16. 2019MeshGAN: Non-linear 3D Morphable Models of Facescited by 39
  17. 2021Spatial Uncertainty-Aware Semi-Supervised Crowd Countingcited by 38
  18. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  19. 2018Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Modelcited by 28
  20. 2017Dense Face Alignmentcited by 24
  21. 2017Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resourcescited by 23
  22. 2019Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoderscited by 22
  23. 2017Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Posescited by 19
  24. 2018Stacked Dense U-Nets with Dual Transformers for Robust Face Alignmentcited by 17
  25. 2021BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentationcited by 9
  26. 2015Pose-Invariant 3D Face Alignmentcited by 8
  27. 2022Counting with Adaptive Auxiliary Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignmentcited by 6
  2. 2024Infinite 3D Landmarks: Improving Continuous 2D Facial Landmark Detectioncited by 2