I'm trying to use face.evoLVe library, which is high-performance Face Recognition Library in PyTorch. Going through the codes, I encountered a list of coordinates named REFERENCE_FACIAL_POINTS which is :
REFERENCE_FACIAL_POINTS = [ # default reference facial points for crop_size = (112, 112); should adjust REFERENCE_FACIAL_POINTS accordingly for other crop_size
[30.29459953, 51.69630051],
[65.53179932, 51.50139999],
[48.02519989, 71.73660278],
[33.54930115, 92.3655014],
[62.72990036, 92.20410156]
]
Further down the code, these numbers are converted into numpy arrays and used heavily everywhere in align_trans.py
I have some questions:
What exactly are these numbers? Reading the comment, I'm certain they are locations for eyes, lips, etc but what exactly do they represent and how are they calculated?
It seems they are tightly coupled with the size of the input image [used in training (at the very least)]. Knowing this, how can one calculate new reference points for newer image sizes?
Are these points for frontal pose only? or will they work on profiles, etc as well? If they don't, how can we add reference points for profiles or other random facial poses?
