Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Face Alignment On Aflw2000 3D

Metrics

Balanced NME (2D Sparse Alignment)

Mean NME(3D Dense Alignment)

Results

Performance results of various models on this benchmark

Model Name	Balanced NME (2D Sparse Alignment)	Mean NME(3D Dense Alignment)	Paper Title	Repository
3DDFA	3.79%	6.55%	Face Alignment in Full Pose Range: A 3D Total Solution
JVCR	3.31%	-	Adversarial Learning Semantic Volume for 2D/3D Face Shape Regression in the Wild
OpNet	3.55%	-	On the power of data augmentation for head pose estimation	-
SynergyNet-Reannotated	2.65%	-	Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
PRN	3.62%	4.40%	Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
SADRNet	3.46%	4.02%	SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
2DASL	3.53%	-	3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild
3DDFA + SDM	4.94%	-	Face Alignment Across Large Poses: A 3D Solution	-
MNN+OR (reannotated)	2.58%	-	Multi-task head pose estimation in-the-wild
DSFNet-f	-	3.8%	DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment
3DSTN	4.49%	-	Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses	-
SynergyNet	3.41%	4.06%	Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
DeFA	4.50%	6.04%	Dense Face Alignment
3DDFA_V2	3.51%	4.18%	Towards Fast, Accurate and Stable 3D Dense Face Alignment

0 of 14 row(s) selected.