segmentation masks?
ldenoue opened this issue · comments
Do you have the ground truth for segmentation masks of where the glasses are on each image?
Specifically, I would like to know the ground-truth masks for pixels that correspond to the glass of the eyeglasses (I'm building an eyeglass segmentation network).
Sorry for that MeGlass dataset only contains images with or without eyeglasses, there are no ground truth masks for eyeglasses. : (