3D on 300W

Metric: NME (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	NME▼	Augmentations	Paper	Date↕	Code
1	DEIL	8.23	No	Unsupervised learning of object frames by dense ...	2017-06-09	-
2	FSE	7.97	No	Unsupervised learning of object landmarks by fac...	2017-05-05	Code
3	3DDFA	7.01	No	Face Alignment Across Large Poses: A 3D Solution	2015-11-23	-
4	Pose-Invariant	6.3	No	Pose-Invariant Face Alignment with a Single CNN	2017-07-19	-
5	CFSS	5.76	No	Face Alignment Across Large Poses: A 3D Solution	2015-11-23	-
6	FAb-Net	5.71	No	Self-supervised learning of a facial attribute e...	2018-08-21	Code
7	DVE	4.65	No	Unsupervised Learning of Landmarks by Descriptor...	2019-08-18	Code
8	SAN GT	3.98	No	Style Aggregated Network for Facial Landmark Det...	2018-03-12	Code
9	TS3	3.49	Yes	Teacher Supervises Students How to Learn From Pa...	2019-08-06	Code
10	Adaloss	3.31	No	Adaloss: Adaptive Loss Function for Landmark Loc...	2019-08-02	Code
11	CHR2C (Inter-ocular Norm)	3.3	No	-	-	Code
12	CNN-CRF (Inter-ocular Norm)	3.3	No	Deep Structured Prediction for Facial Landmark D...	2020-10-18	Code
13	DCFE (Inter-ocular Norm)	3.24	No	-	-	Code
14	3DDE (Inter-ocular Norm)	3.13	No	Face Alignment using a 3D Deeply-initialized Ens...	2019-02-05	Code
15	AnchorFace	3.12	No	AnchorFace: An Anchor-based Facial Landmark Dete...	2020-07-07	Code
16	SPIGA (Inter-ocular Norm)	2.99	No	Shape Preserving Facial Landmarks with Graph Att...	2022-10-13	Code
17	FiFA	2.89	No	Fiducial Focus Augmentation for Facial Landmark ...	2024-02-23	-
18	D-ViT	2.85	No	Cascaded Dual Vision Transformer for Accurate Fa...	2024-11-08	Code

#1DEILSOTA
8.23
NME· 2017-06-09
Unsupervised learning of object frames by dense equivariant image labelling
#2FSESOTA
7.97
NME· 2017-05-05
Unsupervised learning of object landmarks by factorized spatial embeddings Code
#33DDFASOTA
7.01
NME· 2015-11-23
Face Alignment Across Large Poses: A 3D Solution
#4Pose-Invariant
6.3
NME· 2017-07-19
Pose-Invariant Face Alignment with a Single CNN
#5CFSS
5.76
NME· 2015-11-23
Face Alignment Across Large Poses: A 3D Solution
#6FAb-Net
5.71
NME· 2018-08-21
Self-supervised learning of a facial attribute embedding from video Code
#7DVE
4.65
NME· 2019-08-18
Unsupervised Learning of Landmarks by Descriptor Vector Exchange Code
#8SAN GT
3.98
NME· 2018-03-12
Style Aggregated Network for Facial Landmark Detection Code
#9TS3
3.49
NME· Augmentations· 2019-08-06
Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection Code
#10Adaloss
3.31
NME· 2019-08-02
Adaloss: Adaptive Loss Function for Landmark Localization Code
#11CHR2C (Inter-ocular Norm)
3.3
NME
No paperCode
#12CNN-CRF (Inter-ocular Norm)
3.3
NME· 2020-10-18
Deep Structured Prediction for Facial Landmark Detection Code
#13DCFE (Inter-ocular Norm)
3.24
NME
No paperCode
#143DDE (Inter-ocular Norm)
3.13
NME· 2019-02-05
Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees Code
#15AnchorFace
3.12
NME· 2020-07-07
AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses Code
#16SPIGA (Inter-ocular Norm)
2.99
NME· 2022-10-13
Shape Preserving Facial Landmarks with Graph Attention Networks Code
#17FiFA
2.89
NME· 2024-02-23
Fiducial Focus Augmentation for Facial Landmark Detection
#18D-ViT
2.85
NME· 2024-11-08
Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection Code