about evaluating on AFLW2000-3D

microsoft / Deep3DFaceReconstruction

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)

MIT License

2.18k stars 443 forks source link

about evaluating on AFLW2000-3D #99

Closed hao-qiang closed 3 years ago

hao-qiang commented 3 years ago

hi, Great work. You method need alignment the input according to 5 3d landmarks before inference, when evaluating on AFLW2000-3D, which landmarks detector do you use, or just use 5 landmarks from ground truth. Thanks.

YuDeng commented 3 years ago

Hi, for this evaluation, we use an in-house landmark detector to generate 5 landmarks for alignment.