Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees

5 Feb 2019Roberto ValleJosé M. BuenaposadaAntonio ValdésLuis Baumela

Face alignment algorithms locate a set of landmark points in images of faces taken in unrestricted situations. State-of-the-art approaches typically fail or lose accuracy in the presence of occlusions, strong deformations, large pose variations and ambiguous configurations... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Facial Landmark Detection 300W 3DDE (Inter-ocular Norm) NME 3.13 # 1
Face Alignment 300W 3DDE (Inter-ocular Norm) Fullset (public) 3.13 # 3
Face Alignment 300W 3DDE (Inter-pupil Norm) Fullset (public) 4.39 # 12
Facial Landmark Detection AFLW-Full 3DDE (Box height Norm, 19 landmarks - no earlobs) Mean NME 2.01 # 2
Face Alignment COFW 3DDE (Inter-pupil Norm) Mean Error Rate 5.11% # 3
Face Alignment WFLW 3DDE (Inter-ocular Norm) ME (%, all) 4.68% # 4
[email protected] (all) 0.5544 # 5
[email protected](%, all) 5.04% # 5