search

wywu / LAB

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm
https://wywu.github.io/projects/LAB/LAB.html
Other
1.01k stars 273 forks source link

300w dataset--bbox #26

Closed yangyangkiki closed 5 years ago

yangyangkiki commented 5 years ago

Hi,

I am going to repeat your result on 300w dataset and WFLW dataset.

I found that result of face alignment is sensitive to face bounding box. You mentioned in your paper that all training images are cropped and resized to 256*256 according to provided bounding boxes. WFLW provide bbox in the ann file. But 300W dataset provide two different bounding box. One is detected by a face detector, and anther is determined by 68 landmarks.

So which bounding box is used in your experiments? Or any other face detector do you use?

Thank you.

Regards, Kiki

hao-qiang commented 5 years ago

Hi @yangyangkiki I have a question now, the bbox provided in WFLW is the bounding of face, if I crop face according to this and resize to 256*256, the face will be stretched, and the face figures in paper have extra space around face. How do you process this dataset? thank!

FunkyKoki commented 5 years ago

This is also a question for me, wish you would tell me how to determine the bbox, thanks so much!

yangyangkiki commented 5 years ago

Hi @hao-qiang

Unfortunately, this is also a question for me. I did not solve this problem when I want to repeat this experiment. Hope somebody can tell us.