Open XuefengLi1 opened 2 years ago
Thanks for your great work! Could you provide more details about how the depth metric is calculated in the experiments?
According to the paper: "calculating MSE against pseudo-ground-truth depth-maps (Depth) and poses (Pose) estimated from synthesized images by [10];"
I found Deep3DFaceRecon only gives a face mesh file (not covering the whole input image), and a .mat file including 257-dimensional coefficients and 68 projected 2d facial landmarks. Could you please share more details about how the depth MSE is calculated in the experiments using these results from Deep3DFaceRecon?
Thanks!
Hi! @XuefengLi1
Did you figure out any details about depth MSE? I'm struggling to get pseudo-ground-truth depth-maps.
Thanks!
Thanks for your great work! Could you provide more details about how the depth metric is calculated in the experiments?
According to the paper: "calculating MSE against pseudo-ground-truth depth-maps (Depth) and poses (Pose) estimated from synthesized images by [10];"
I found Deep3DFaceRecon only gives a face mesh file (not covering the whole input image), and a .mat file including 257-dimensional coefficients and 68 projected 2d facial landmarks. Could you please share more details about how the depth MSE is calculated in the experiments using these results from Deep3DFaceRecon?
Thanks!