erkil1452 / gaze360

Code for the Gaze360: Physically Unconstrained Gaze Estimation in the Wild Dataset
http://gaze360.csail.mit.edu
Other
225 stars 42 forks source link

How to get mean angular errors #48

Closed LinReseach closed 2 years ago

LinReseach commented 2 years ago

Hi,Petr.Thanks for your work.I have a question to your paper 'Gaze360: Physically Unconstrained Gaze Estimation in the Wild'.In table2 you reports the mean angular errors for various models.How you get this mean angular error? (yaw error+pitch error)/2?

erkil1452 commented 2 years ago

Hi, we convert both gaze vectors (prediction and GT) into cartesian coordinate system g=(x,y,z), normalize their lengths and the compute the angle between them as error=arccos(dot(g1,g2))