P3d Debinarizer -

# Distance transform from the binary edges dist_transform = cv2.distanceTransform(binary_mask, cv2.DIST_L2, 5) # Normalize to 0-255 debinarized_distance = cv2.normalize(dist_transform, None, 0, 255, cv2.NORM_MINMAX).astype(np.uint8) plt.imshow(debinarized_distance, cmap='gray') plt.title('Distance Transform Debinarizer') plt.show()

The loss function for a typical deep learning P3D debinarizer looks like this: p3d debinarizer

[ \mathcalL = |I_pred - I_gt| 2^2 + \lambda_1 |\nabla I pred - \nabla I_gt| 1 + \lambda_2 |I pred \cdot B - I_gt \cdot B|_1 ] # Distance transform from the binary edges dist_transform

The P3D approach adds a third dimension: or spatial depth . p3d debinarizer

import torch import torch.nn as nn class SimpleP3DUNet(nn.Module): def (self): super(). init () self.encoder = nn.Sequential( nn.Conv2d(2, 64, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), nn.Conv2d(64, 128, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), nn.Conv2d(128, 256, 3, padding=1), nn.ReLU() ) self.decoder = nn.Sequential( nn.ConvTranspose2d(256, 128, 2, stride=2), nn.ReLU(), nn.ConvTranspose2d(128, 64, 2, stride=2), nn.ReLU(), nn.Conv2d(64, 1, 3, padding=1), nn.Sigmoid() )