HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Facial Landmark Detection On 300W

평가 지표

NME

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	NME	Paper Title	Repository
CNN-CRF (Inter-ocular Norm)	3.30	Deep Structured Prediction for Facial Landmark Detection
CFSS	5.76	Face Alignment Across Large Poses: A 3D Solution	-
D-ViT	2.85	Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection
3DDE (Inter-ocular Norm)	3.13	Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees
SAN GT	3.98	Style Aggregated Network for Facial Landmark Detection
FPN	-	FacePoseNet: Making a Case for Landmark-Free Face Alignment
Pose-Invariant	6.30	Pose-Invariant Face Alignment with a Single CNN	-
AnchorFace	3.12	AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses
CHR2C (Inter-ocular Norm)	3.3	Cascade of Encoder-Decoder CNNs with Learned Coordinates Regressor for Robust Facial Landmarks Detection	-
Adaloss	3.31	Adaloss: Adaptive Loss Function for Landmark Localization
SPIGA (Inter-ocular Norm)	2.99	Shape Preserving Facial Landmarks with Graph Attention Networks
DCFE (Inter-ocular Norm)	3.24	A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment	-
FiFA	2.89	Fiducial Focus Augmentation for Facial Landmark Detection	-
3DDFA	7.01	Face Alignment Across Large Poses: A 3D Solution	-
TS3	3.49	Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

0 of 15 row(s) selected.