Closed vadimkantorov closed 6 years ago
Hi! The code is very similar compared to the PhotoWCT code of NVidia, except one line:
https://github.com/NVIDIA/FastPhotoStyle/blob/master/photo_smooth.py#L79 : vals = (1/win_size)*(1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
vals = (1/win_size)*(1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
https://github.com/MarcoForte/closed-form-matting/blob/master/closed_form_matting.py#L100 : vals = np.eye(win_size) - (1.0/win_size)*(1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
vals = np.eye(win_size) - (1.0/win_size)*(1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
Does it mean your function computes 1 - L intead?
1 - L
Hi! The code is very similar compared to the PhotoWCT code of NVidia, except one line:
https://github.com/NVIDIA/FastPhotoStyle/blob/master/photo_smooth.py#L79 :
vals = (1/win_size)*(1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
https://github.com/MarcoForte/closed-form-matting/blob/master/closed_form_matting.py#L100 :
vals = np.eye(win_size) - (1.0/win_size)*(1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
Does it mean your function computes
1 - L
intead?