FacePoseNet: Making a Case for Landmark-Free Face Alignment

24 Aug 2017Fengju ChangAnh Tuan TranTal HassnerIacopo MasiRam NevatiaGerard Medioni

We show how a simple convolutional neural network (CNN) can be trained to accurately and robustly regress 6 degrees of freedom (6DoF) 3D head pose, directly from image intensities. We further explain how this FacePoseNet (FPN) can be used to align faces in 2D and 3D as an alternative to explicit facial landmark detection for these tasks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Facial Landmark Detection 300W FPN Mean Error Rate 0.1043 # 1
Face Verification IJB-A FPN TAR @ FAR=0.01 90.1% # 10
Face Identification IJB-A FPN Accuracy 91.4% # 2
Face Verification IJB-B FPN TAR @ FAR=0.01 96.5% # 1
Face Identification IJB-B FPN Accuracy 91.1% # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet