SOTAVerified

Facial Landmark Detection

Facial Landmark Detection is a computer vision task that involves detecting and localizing specific points or landmarks on a face, such as the eyes, nose, mouth, and chin. The goal is to accurately identify these landmarks in images or videos of faces in real-time and use them for various applications, such as face recognition, facial expression analysis, and head pose estimation.

( Image credit: Style Aggregated Network for Facial Landmark Detection )

Papers

Showing 101125 of 139 papers

TitleStatusHype
Laplace Landmark Localization0
Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos0
Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble0
Leveraging Datasets With Varying Annotations for Face Alignment via Deep Regression Network0
Limitations and Biases in Facial Landmark Detection -- An Empirical Study on Older Adults with Dementia0
Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection0
FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred VideosCode0
Face Alignment using a 3D Deeply-initialized Ensemble of Regression TreesCode0
FacePoseNet: Making a Case for Landmark-Free Face AlignmentCode0
ExpNet: Landmark-Free, Deep, 3D Facial ExpressionsCode0
Precise Facial Landmark Detection by Dynamic Semantic Aggregation TransformerCode0
Learning to Impute: A General Framework for Semi-supervised LearningCode0
Can Synthetic Faces Undo the Damage of Dataset Bias to Face Recognition and Facial Landmark Detection?Code0
Unsupervised Learning of Landmarks by Descriptor Vector ExchangeCode0
ACR Loss: Adaptive Coordinate-based Regression Loss for Face AlignmentCode0
Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion modelCode0
Look at Boundary: A Boundary-Aware Face Alignment AlgorithmCode0
Combining Data-driven and Model-driven Methods for Robust Facial Landmark DetectionCode0
Facial Landmark Points Detection Using Knowledge Distillation-Based Neural NetworksCode0
A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark DetectionCode0
3FabRec: Fast Few-shot Face alignment by ReconstructionCode0
Fast Localization of Facial Landmark PointsCode0
A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face AlignmentCode0
Cascade of Encoder-Decoder CNNs with Learned Coordinates Regressor for Robust Facial Landmarks DetectionCode0
Style Aggregated Network for Facial Landmark DetectionCode0
Show:102550
← PrevPage 5 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
13DDFANME7.01Unverified
2Pose-InvariantNME6.3Unverified
3CFSSNME5.76Unverified
4SAN GTNME3.98Unverified
5TS3NME3.49Unverified
6AdalossNME3.31Unverified
7CHR2C (Inter-ocular Norm)NME3.3Unverified
8CNN-CRF (Inter-ocular Norm)NME3.3Unverified
9DCFE (Inter-ocular Norm)NME3.24Unverified
103DDE (Inter-ocular Norm)NME3.13Unverified
#ModelMetricClaimedVerifiedStatus
1HPRNet (Hourglass-104)keypoint AP75.4Unverified
2HPRNet (DLA)keypoint AP74.6Unverified
3HPRNet (Hourglass-104)keypoint AP59.4Unverified
4HPRNet (DLA)keypoint AP55.2Unverified
5HPRNet (Hourglass-104)keypoint AP50.4Unverified
6HPRNet (DLA)keypoint AP47Unverified
#ModelMetricClaimedVerifiedStatus
1DCFE (Box height Norm, 19 landmarks - no earlobs)Mean NME 2.17Unverified
23DDE (Box height Norm, 19 landmarks - no earlobs)Mean NME2.01Unverified
3SANMean NME 1.91Unverified
4AnchorFaceMean NME 1.56Unverified
5FiFAMean NME 0.92Unverified
#ModelMetricClaimedVerifiedStatus
1SANMean NME 1.85Unverified
2AnchorFaceMean NME1.38Unverified
3FiFAMean NME0.8Unverified
#ModelMetricClaimedVerifiedStatus
1ELD (MobileNetV2)NME3.09Unverified
2ELD (EfficientNetV2B0)NME2.98Unverified
3ELD (EfficientNetV2S)NME2.83Unverified
#ModelMetricClaimedVerifiedStatus
1ELD (EfficientNetV2B1)NME4.65Unverified
2FiFANME (inter-ocular)3.89Unverified
3D-ViTNME3.75Unverified
#ModelMetricClaimedVerifiedStatus
1CPM+SBR+PAMAUC0.08 private59.39Unverified
2CPM+SBRAUC0.08 private58.22Unverified
#ModelMetricClaimedVerifiedStatus
1AnchorFaceMean NME 3.72Unverified
2TS3Mean NME 3.49Unverified
#ModelMetricClaimedVerifiedStatus
1D-ViTNME (inter-pupil)4.13Unverified
2FiFANME (inter-ocular)2.96Unverified
#ModelMetricClaimedVerifiedStatus
1JVCRGTE7.28Unverified