| STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection | ✓ Link | 2.87 | 2.52 | 4.32 | 4.03 | 3.5 | 6.22 | STAR | 2023-06-05 |
| FreeEnricher: Enriching Face Landmarks without Additional Cost | | 2.87 | | | | | | ADNet-FE5 | 2022-12-19 |
| General Facial Representation Learning in a Visual-Linguistic Manner | ✓ Link | 2.88 | 2.50 | 4.42 | 4.05 | 3.46 | 6.38 | FaRL-B (epoch 64) | 2021-12-06 |
| Fiducial Focus Augmentation for Facial Landmark Detection | | 2.89 | 2.51 | 4.47 | | | | FiFA | 2024-02-23 |
| ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment | ✓ Link | 2.93 | 2.53 | 4.58 | 4.08 | 3.51 | 6.47 | ADNet | 2021-09-13 |
| General Facial Representation Learning in a Visual-Linguistic Manner | ✓ Link | 2.93 | 2.56 | 4.45 | 4.11 | 3.53 | 6.42 | FaRL-B (epoch 16) | 2021-12-06 |
| PropagationNet: Propagate Points to Curve to Learn Structure Information | | 2.93 | 2.67 | 3.99 | 4.1 | 3.7 | 5.75 | PropNet | 2020-06-25 |
| Subpixel Heatmap Regression for Facial Landmark Localization | | 2.94 | 2.61 | 4.13 | | | | SHR-FAN | 2021-11-03 |
| Towards Accurate Facial Landmark Detection via Cascaded Transformers | | 2.96 | 2.6 | 4.48 | | | | DTLD+ | 2022-08-23 |
| Shape Preserving Facial Landmarks with Graph Attention Networks | ✓ Link | 2.99 | 2.59 | 4.66 | 4.20 | 3.59 | 6.73 | SPIGA | 2022-10-13 |
| Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression | ✓ Link | 3.07 | 2.72 | 4.52 | 4.31 | 3.77 | 6.52 | AWing | 2019-04-16 |
| HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap | ✓ Link | 3.09 | 2.65 | 4.89 | | | | HIH | 2021-04-07 |
| When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model | | 3.09 | 2.73 | 4.6 | | | | BarrelNet (ResNet-101) | 2021-05-27 |
| Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement | | 3.12 | 2.71 | 4.78 | 4.37 | 3.76 | 6.89 | GRegNet + LRefNet | 2019-06-16 |
| Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees | ✓ Link | 3.13 | 2.69 | 4.92 | 4.39 | 3.73 | 7.10 | 3DDE | 2019-02-05 |
| ATF: Towards Robust Face Alignment via Leveraging Similarity and Diversity across Different Datasets | ✓ Link | 3.17 | 2.75 | 4.89 | | | | ATF | 2020-10-12 |
| Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning | ✓ Link | 3.17 | 2.75 | 4.90 | | | | SLPT | 2022-03-13 |
| Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild | ✓ Link | 3.19 | 2.78 | 4.89 | | | | PIPNet (ResNet-101) | 2020-03-08 |
| A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment | ✓ Link | 3.24 | 2.76 | 5.22 | 4.55 | 3.83 | 7.54 | DCFE | 2018-09-01 |
| Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble | | 3.28 | 2.85 | 5.03 | | | | HG-HSLE | 2019-10-01 |
| Fast and Accurate: Structure Coherence Component for Face Alignment | | 3.28 | 2.88 | 4.93 | | | | SCC | 2020-06-21 |
| Cascade of Encoder-Decoder CNNs with Learned Coordinates Regressor for Robust Facial Landmarks Detection | ✓ Link | 3.3 | 2.85 | 5.15 | 4.64 | 3.96 | 7.44 | CHR2C | 2019-10-15 |
| Deep Structured Prediction for Facial Landmark Detection | ✓ Link | 3.30 | 2.93 | 4.84 | 4.63 | 4.06 | 6.98 | CNN-CRF | 2020-10-18 |
| High-Resolution Representations for Labeling Pixels and Regions | ✓ Link | 3.32 | 2.87 | 5.15 | | | | HR-Net | 2019-04-09 |
| Deep High-Resolution Representation Learning for Visual Recognition | ✓ Link | 3.32 | 2.87 | 5.15 | | | | HRNet | 2019-08-20 |
| DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild | | 3.39 | 2.93 | 5.26 | | | | DeCaFA | 2019-04-04 |
| Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data | | 3.42 | 2.97 | 5.30 | | | | FASE | 2022-09-16 |
| Deep Alignment Network: A convolutional neural network for robust face alignment | ✓ Link | 3.44 | 3.09 | 4.88 | 4.83 | 4.29 | 7.05 | DAN-Menpo | 2017-06-06 |
| Look at Boundary: A Boundary-Aware Face Alignment Algorithm | ✓ Link | 3.49 | 2.98 | 5.19 | 4.12 | 3.42 | 6.98 | LAB | 2018-05-26 |
| LDDMM-Face: Large Deformation Diffeomorphic Metric Learning for Flexible and Consistent Face Alignment | | 3.53 | 3.07 | 5.4 | | | | LDDMM-Face | 2021-08-02 |
| AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses | ✓ Link | 3.72 | 3.12 | 6.19 | | | | AnchorFace | 2020-07-07 |
| ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment | ✓ Link | 3.75 | 3.36 | 5.36 | | | | EF-3ACR | 2022-03-29 |
| 3FabRec: Fast Few-shot Face alignment by Reconstruction | ✓ Link | 3.82 | 3.36 | 5.74 | | | | 3FabRec | 2019-11-24 |
| Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation | ✓ Link | 3.86 | 3.21 | 6.49 | | | | AVS | 2019-08-18 |
| SCAF: Skip-Connections in Auto-encoder for Face alignment with few annotated data | | 3.95 | 3.48 | 5.83 | | | | SCAF | 2022-05-15 |
| Style Aggregated Network for Facial Landmark Detection | ✓ Link | 3.98 | 3.34 | 6.60 | | | | SAN | 2018-03-12 |
| Laplace Landmark Localization | | 4.01 | 3.28 | 7.01 | | | | LaplaceKL | 2019-03-27 |
| Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks | ✓ Link | 4.06 | 3.56 | 6.13 | | | | MobileNetV2+KD-Loss | 2021-11-13 |
| Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks | | 4.17 | 3.56 | 6.67 | | | | ODN | 2019-06-01 |
| ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation | ✓ Link | 4.59 | 3.88 | 7.35 | | | | MobileNetV2 | 2021-02-27 |
| Improving Landmark Localization with Semi-Supervised Learning | | 4.90 | 4.20 | 7.78 | | | | RCN | 2017-09-05 |
| ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation | ✓ Link | 5.50 | 4.82 | 8.2 | | | | ASMNet | 2021-02-27 |
| Face Alignment in Full Pose Range: A 3D Total Solution | ✓ Link | 5.63 | 5.09 | 8.07 | 7.01 | 6.15 | 10.59 | 3DDFA | 2018-04-02 |
| 3D face reconstruction with dense landmarks | | | 3.03 | 4.8 | | | | DenseLandmarks (GNLL) | 2022-04-06 |
| Fake It Till You Make It: Face analysis in the wild using synthetic data alone | | | 3.09 | 4.86 | | | | FakeIt | 2021-09-30 |
| Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection | | | | | 4.02 | 3.45 | 6.38 | HGs + SA + Norm + GHCU | 2019-03-26 |
| Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks | ✓ Link | | | | 4.04 | 3.27 | 7.18 | Wing | 2017-11-17 |
| Facial Landmarks Detection by Self-Iterative Regression based Landmarks-Attention Network | | | | | 5.04 | 4.29 | 8.14 | SIR-LAN | 2018-03-18 |