Face Alignment On Wflw

评估指标

AUC@10 (inter-ocular)

FR@10 (inter-ocular)

NME (inter-ocular)

评测结果

各个模型在此基准测试上的表现结果

模型名称	AUC@10 (inter-ocular)	FR@10 (inter-ocular)	NME (inter-ocular)	Paper Title	Repository
LDEQ	62.4	2.48	3.92	Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models
STAR	60.5	2.32	4.02	STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection
FiFA	61.78	1.60	3.89	Fiducial Focus Augmentation for Facial Landmark Detection	-
GRegNet + LRefNet	58.4	4.88	4.65	Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement	-
DVLN	45.6	10.84	10.84	Leveraging intra and inter-dataset variations for robust face alignment	-
LOTR-HR	60.14	3.52	4.31	LOTR: Face Landmark Localization Using Localization Transformer	-
LAB	53.2	7.56	5.27	Look at Boundary: A Boundary-Aware Face Alignment Algorithm
DeCaFA	56.3	4.84	4.62	DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild	-
CFSS	36.6	20.56	9.07	Face alignment by coarse-to-fine shape searching
CHR2C	57.55	3.55	4.39	Cascade of Encoder-Decoder CNNs with Learned Coordinates Regressor for Robust Facial Landmarks Detection
ATPN	55.7	6.27	5.13	An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking	-
SCC	56.66	2.88	4.4	Fast and Accurate: Structure Coherence Component for Face Alignment	-
3DDE	55.44	5.04	4.68	Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees
LUVLi	57.7	3.12	4.37	LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
DTLD+	-	2.68	4.05	Towards Accurate Facial Landmark Detection via Cascaded Transformers	-
MobileNetV2	-	-	9.41	ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation	-
HIH	60.5	2.60	4.08	HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap
AVS	59.13	4.08	4.39	Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation	-
SLPT	59.5	2.76	4.14	Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning
FASE	-	-	4.62	Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data	-

0 of 36 row(s) selected.