“…
denotes the pixel‐wise binary material‐specific mask generated from the classification branch.
denotes the image gradient correlation based regularizer
28,31 that ensured edge consistency in both material domain and DECT image domain,
denoted the anisotropic form of image gradient,
denoted Pearson correlation, and ε was a small constant (fixed at
).
is the feature reconstruction loss
33 that ensured high‐level texture consistency between the mixed images
and
by matching the high‐level features extracted from the l th convolutional layer (empirically fixed at the 15th layer) of a pretrained VGG‐19 neural network
,
and
were the mixed images from
and
…”