NME (inter-ocular): 3.81%
Papers with Code · CC BY-SA 4.0
Face Alignment
Face alignment is the task of identifying the geometric structure of faces in digital images, and attempting to obtain a canonical alignment of the face based on translation, scale, and rotation.
<span style="color:grey; opacity: 0.6">( Image credit: 3DDFA_V2 )</span>
논문
NME (inter-ocular): 3.92%
NME (inter-pupil): 5.04%Recall at 80% precision (Landmarks Visibility): 72.12
NME (inter-ocular): 3.02%
NME (inter-pupil): 5.27%
NME (inter-ocular): 3.47%
ATF: Towards Robust Face Alignment via Leveraging Similarity and Diversity across Different Datasets
NME (inter-ocular): 3.32%
NME (inter-pupil): 5.09%
NME (inter-ocular): 3.45
NME (inter-ocular): 5.77%
NME (inter-pupil): 5.11%Recall at 80% precision (Landmarks Visibility): 63.89
NME (inter-ocular): 3.63%
NME (inter-ocular): 2.96
NME (inter-ocular): 3.45%
NME (inter-ocular): 3.21%
NME (bbox): 2.10AUC@7 (bbox): 70.2
NME (inter-ocular): 3.08%
NME (inter-ocular): 3.32
NME (inter-ocular): 3.71%
NME (inter-ocular): 3.28%
NME (inter-ocular): 3.32NME (inter-pupil): 4.79
NME (inter-pupil): 5.55%
NME (inter-ocular): 3.21%NME (inter-pupil): 4.62
NME (inter-ocular): 3.02%
NME (inter-ocular): 3.1%
NME (inter-ocular): 5.07