src/methods/domer/image-colorization/network.ipynb

+%% Cell type:code id: tags:
+
+``` 
+from network import ColorizeNet
+
+model = ColorizeNet()
+model
+```
+
+%% Output
+
+    ColorizeNet(
+      (encoder): Sequential(
+        (0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
+        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+        (2): ReLU(inplace=True)
+        (3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
+        (4): Sequential(
+          (0): BasicBlock(
+            (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+          (1): BasicBlock(
+            (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+        (5): Sequential(
+          (0): BasicBlock(
+            (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (downsample): Sequential(
+              (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
+              (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            )
+          )
+          (1): BasicBlock(
+            (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+          )
+        )
+      )
+      (decoder): Sequential(
+        (0): Sequential(
+          (0): BasicBlock(
+            (conv1): Conv2d(128, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
+            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (res_conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (res_bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (upsample): Upsample(scale_factor=2.0, mode=nearest)
+          )
+          (1): BasicBlock(
+            (conv1): Conv2d(64, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
+            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (activation): ReLU(inplace=True)
+          )
+        )
+        (1): Sequential(
+          (0): BasicBlock(
+            (conv1): Conv2d(64, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
+            (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (res_conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (res_bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (upsample): Upsample(scale_factor=2.0, mode=nearest)
+          )
+          (1): BasicBlock(
+            (conv1): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
+            (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (activation): ReLU(inplace=True)
+          )
+        )
+        (2): Sequential(
+          (0): BasicBlock(
+            (conv1): Conv2d(32, 2, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
+            (bn1): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(2, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (res_conv): Conv2d(32, 2, kernel_size=(1, 1), stride=(1, 1), bias=False)
+            (res_bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (upsample): Upsample(scale_factor=2.0, mode=nearest)
+          )
+          (1): BasicBlock(
+            (conv1): Conv2d(2, 2, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
+            (bn1): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (relu): ReLU(inplace=True)
+            (conv2): Conv2d(2, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
+            (bn2): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
+            (activation): Sigmoid()
+          )
+        )
+      )
+    )
+
+%% Cell type:code id: tags:
+
+``` 
+import torch
+
+# to check if our model is working as expected
+model(torch.rand((2, 1, 224, 224))).shape
+```
+
+%% Output
+
+    torch.Size([2, 2, 224, 224])
+
+%% Cell type:code id: tags:
+
+``` 
+from utils import count_params
+
+count_params(model)  # no of trainable parameters
+```
+
+%% Output
+
+    1166016

src/methods/domer/image-colorization/network.py

+import torch.nn as nn
+import torchvision.models as models
+
+
+class BasicBlock(nn.Module):
+    def __init__(self, in_channels, out_channels,
+                 activation=None, upsample=None):
+        super().__init__()
+
+        self.conv1 = nn.Conv2d(
+            in_channels=in_channels, out_channels=out_channels,
+            kernel_size=5, stride=1, padding=2, bias=False
+        )
+        self.bn1 = nn.BatchNorm2d(num_features=out_channels)
+        self.relu = nn.ReLU(inplace=True)
+        self.conv2 = nn.Conv2d(
+            in_channels=out_channels, out_channels=out_channels,
+            kernel_size=3, stride=1, padding=1, bias=False
+        )
+        self.bn2 = nn.BatchNorm2d(num_features=out_channels)
+
+        if activation is not None:
+            self.activation = activation
+        else:
+            self.res_conv = nn.Conv2d(
+                in_channels=in_channels, out_channels=out_channels,
+                kernel_size=1, stride=1, bias=False
+            )
+            self.res_bn = nn.BatchNorm2d(num_features=out_channels)
+
+        self.upsample = upsample
+
+    def forward(self, t):
+
+        res = t
+        t = self.conv1(t)
+        t = self.bn1(t)
+        t = self.relu(t)
+        t = self.conv2(t)
+        t = self.bn2(t)
+
+        if self.upsample is not None:
+            res = self.res_conv(res)
+            res = self.res_bn(res)
+            t += res
+            t = self.relu(t)
+            t = self.upsample(t)
+        else:
+            t += res
+            t = self.activation(t)
+
+        return t
+
+
+class ColorizeNet(nn.Module):
+    def __init__(self):
+        super().__init__()
+
+        # make pretrained=True before starting the training process
+        resnet18 = models.resnet18(pretrained=False)
+        # change first conv layer to accept single channel (grayscale)
+        resnet18.conv1.weight = nn.Parameter(
+            resnet18.conv1.weight.mean(dim=1).unsqueeze(dim=1))
+
+        # use first 3 layers of ResNet-18 as encoder
+        self.encoder = nn.Sequential(
+            *list(resnet18.children())[:6]
+        )
+        self.decoder = nn.Sequential(
+            self._make_layer(BasicBlock, 128, 64, nn.ReLU(inplace=True)),
+            self._make_layer(BasicBlock, 64, 32, nn.ReLU(inplace=True)),
+            self._make_layer(BasicBlock, 32, 2, nn.Sigmoid())
+        )
+
+    def _make_layer(self, block, in_channels, out_channels, activation):
+        upsample = nn.Upsample(scale_factor=2, mode='nearest')
+        layers = []
+        layers.append(block(in_channels, out_channels, upsample=upsample))
+        layers.append(block(out_channels, out_channels, activation=activation))
+
+        return nn.Sequential(*layers)
+
+    def forward(self, t):
+        t = self.encoder(t)
+        t = self.decoder(t)
+
+        return t

src/methods/domer/image-colorization/requirements.txt

+matplotlib==3.3.2
+numpy==1.19.4
+Pillow==8.0.1
+scikit-image==0.17.2
+torch==1.7.0+cpu
+torchvision==0.8.1+cpu
+tqdm==4.51.0
\ No newline at end of file

src/methods/domer/image-colorization/train.ipynb

+%% Cell type:code id: tags:
+
+``` 
+# from google.colab import drive
+# drive.mount('/content/drive')
+```
+
+%% Output
+
+    Mounted at /content/drive
+
+%% Cell type:code id: tags:
+
+``` 
+# Download and unzip (2.2GB)
+# !wget http://data.csail.mit.edu/places/places205/testSetPlaces205_resize.tar.gz
+# !mkdir images/
+# !tar -xzf drive/MyDrive/testSetPlaces205_resize.tar.gz -C 'images/'
+```
+
+%% Cell type:code id: tags:
+
+``` 
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torchvision.transforms as transforms
+
+from tqdm import tqdm
+from network import ColorizeNet
+from utils import GrayscaleImageFolder
+```
+
+%% Cell type:code id: tags:
+
+``` 
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+```
+
+%% Cell type:code id: tags:
+
+``` 
+transform = transforms.Compose([
+    transforms.RandomResizedCrop(224),
+    transforms.RandomHorizontalFlip()
+])
+
+train_set = GrayscaleImageFolder('images/', transform=transform)
+train_loader = torch.utils.data.DataLoader(train_set, batch_size=128, shuffle=True, num_workers=4)
+```
+
+%% Cell type:code id: tags:
+
+``` 
+criterion = nn.MSELoss()
+
+model = ColorizeNet().to(device)
+optimizer = optim.Adam(model.parameters(), lr=0.001)
+# scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[8, 24], gamma=1/3)
+scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, factor=1/3, patience=5, verbose=True)
+```
+
+%% Cell type:code id: tags:
+
+``` 
+try:
+    checkpoint = torch.load('drive/MyDrive/checkpoint_0.001.pth', map_location=device)
+    start_epoch = checkpoint['next_epoch']
+    model.load_state_dict(checkpoint['model'])
+    optimizer.load_state_dict(checkpoint['optimizer'])
+    scheduler.load_state_dict(checkpoint['scheduler'])
+
+except:
+    start_epoch = 0
+```
+
+%% Cell type:code id: tags:
+
+``` 
+num_epochs = 64
+for epoch in range(start_epoch, num_epochs):
+    train_loss = 0
+    loop = tqdm(train_loader)
+    for batch in loop:
+        in_gray, in_ab = batch[0].to(device), batch[1].to(device)
+        out_ab = model(in_gray)
+        loss = criterion(out_ab, in_ab)
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        train_loss += loss.item()*in_gray.size(0)
+        loop.set_description(f'Epoch [{epoch+1:2d}/{num_epochs}]')
+        loop.set_postfix(loss=train_loss)
+
+    scheduler.step(train_loss)
+    checkpoint = {
+        'next_epoch': epoch + 1,
+        'model': model.state_dict(),
+        'optimizer': optimizer.state_dict(),
+        'scheduler': scheduler.state_dict()
+    }
+    torch.save(checkpoint, f'drive/MyDrive/checkpoint_{scheduler._last_lr[0]}.pth')
+```
+
+%% Output
+
+    Epoch [39/64]: 100%|██████████| 321/321 [12:00<00:00,  2.24s/it, loss=97.4]
+    Epoch [40/64]: 100%|██████████| 321/321 [11:30<00:00,  2.15s/it, loss=98]
+    Epoch [41/64]: 100%|██████████| 321/321 [11:18<00:00,  2.12s/it, loss=97.4]
+    Epoch [42/64]: 100%|██████████| 321/321 [11:28<00:00,  2.15s/it, loss=103]
+    Epoch [43/64]: 100%|██████████| 321/321 [11:23<00:00,  2.13s/it, loss=98.4]
+    Epoch [44/64]: 100%|██████████| 321/321 [11:15<00:00,  2.10s/it, loss=97.3]
+    Epoch [45/64]: 100%|██████████| 321/321 [11:29<00:00,  2.15s/it, loss=97.6]
+    Epoch [46/64]: 100%|██████████| 321/321 [11:25<00:00,  2.14s/it, loss=96.5]
+    Epoch [47/64]: 100%|██████████| 321/321 [11:40<00:00,  2.18s/it, loss=96.7]
+    Epoch [48/64]: 100%|██████████| 321/321 [11:44<00:00,  2.19s/it, loss=96.3]
+    Epoch [49/64]: 100%|██████████| 321/321 [11:13<00:00,  2.10s/it, loss=96.5]
+    Epoch [50/64]: 100%|██████████| 321/321 [11:09<00:00,  2.09s/it, loss=96.4]
+    Epoch [51/64]: 100%|██████████| 321/321 [11:09<00:00,  2.09s/it, loss=95.7]
+    Epoch [52/64]: 100%|██████████| 321/321 [11:13<00:00,  2.10s/it, loss=95.9]
+    Epoch [53/64]: 100%|██████████| 321/321 [11:08<00:00,  2.08s/it, loss=95.8]
+    Epoch [54/64]: 100%|██████████| 321/321 [11:31<00:00,  2.15s/it, loss=95.4]
+    Epoch [55/64]: 100%|██████████| 321/321 [11:54<00:00,  2.23s/it, loss=95.5]
+    Epoch [56/64]: 100%|██████████| 321/321 [12:11<00:00,  2.28s/it, loss=95.5]
+    Epoch [57/64]: 100%|██████████| 321/321 [12:00<00:00,  2.24s/it, loss=94.9]
+    Epoch [58/64]: 100%|██████████| 321/321 [11:54<00:00,  2.23s/it, loss=94.9]
+    Epoch [59/64]: 100%|██████████| 321/321 [11:56<00:00,  2.23s/it, loss=94.9]
+    Epoch [60/64]: 100%|██████████| 321/321 [12:06<00:00,  2.26s/it, loss=94.3]
+    Epoch [61/64]: 100%|██████████| 321/321 [12:03<00:00,  2.26s/it, loss=95]
+    Epoch [62/64]: 100%|██████████| 321/321 [12:01<00:00,  2.25s/it, loss=95]
+    Epoch [63/64]: 100%|██████████| 321/321 [12:05<00:00,  2.26s/it, loss=96.7]
+    Epoch [64/64]: 100%|██████████| 321/321 [12:10<00:00,  2.27s/it, loss=95]
+
+%% Cell type:code id: tags:
+
+``` 
+torch.save(model.state_dict(), f'./models/model.pth')  # save the model separately from the checkpoint file
+```

src/methods/domer/image-colorization/utils.py

+import torch
+from torchvision import transforms, datasets
+import numpy as np
+from PIL import Image
+from skimage.color import rgb2lab, rgb2gray, lab2rgb
+
+
+def count_params(model):
+    '''
+    returns the number of trainable parameters in some model
+    '''
+    return sum(p.numel() for p in model.parameters() if p.requires_grad)
+
+
+class GrayscaleImageFolder(datasets.ImageFolder):
+    '''
+    Custom dataloader for various operations on images before loading them.
+    '''
+
+    def __getitem__(self, index):
+        path, target = self.imgs[index]
+        img = self.loader(path)
+        if self.transform is not None:
+            img_orig = self.transform(img)  # apply transforms
+            img_orig = np.asarray(img_orig)  # convert to numpy array
+            img_lab = rgb2lab(img_orig)  # convert RGB image to LAB
+            img_ab = img_lab[:, :, 1:3]  # separate AB channels from LAB
+            img_ab = (img_ab + 128) / 255  # normalize the pixel values
+            # transpose image from HxWxC to CxHxW and turn it into a tensor
+            img_ab = torch.from_numpy(img_ab.transpose((2, 0, 1))).float()
+            img_orig = rgb2gray(img_orig)  # convert RGB to grayscale
+            # add a channel axis to grascale image and turn it into a tensor
+            img_orig = torch.from_numpy(img_orig).unsqueeze(0).float()
+
+        if self.target_transform is not None:
+            target = self.target_transform(target)
+
+        return img_orig, img_ab, target
+
+
+def load_gray(path, max_size=360, shape=None):
+    '''
+    load an image as grayscale, change the shape as per input,
+    perform transformations and convert it to model compatable shape.
+    '''
+    img_gray = Image.open(path).convert('L')
+
+    if max(img_gray.size) > max_size:
+        size = max_size
+    else:
+        size = max(img_gray.size)
+
+    if shape is not None:
+        size = shape
+
+    img_transform = transforms.Compose([
+        transforms.Resize(size),
+        transforms.ToTensor()
+    ])
+
+    img_gray = img_transform(img_gray).unsqueeze(0)
+    return img_gray
+
+
+def to_rgb(img_l, img_ab):
+    '''
+    concatinates Lightness (grayscale) and AB channels,
+    and converts the resulting LAB image to RGB
+    '''
+    if img_l.shape == img_ab.shape:
+        img_lab = torch.cat((img_l, img_ab), 1).numpy().squeeze()
+    else:
+        img_lab = torch.cat(
+            (img_l, img_ab[:, :, :img_l.size(2), :img_l.size(3)]),
+            dim=1
+        ).numpy().squeeze()
+
+    img_lab = img_lab.transpose(1, 2, 0)  # transpose image to HxWxC
+    img_lab[:, :, 0] = img_lab[:, :, 0] * 100  # range pixel values from 0-100
+    img_lab[:, :, 1:] = img_lab[:, :, 1:] * 255 - 128  # un-normalize
+    img_rgb = lab2rgb(img_lab.astype(np.float64))  # convert LAB image to RGB
+
+    return img_rgb

src/methods/domer/reconstruct.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Jan 30 19:35:12 2024
+
+@author: stani1
+"""
+
+"""The main file for the baseline reconstruction.
+This file should NOT be modified.
+"""
+
+
+import numpy as np
+from PIL import Image
+import subprocess
+import os
+
+
+from src.forward_model import CFA
+from src.methods.baseline.demo_reconstruction import naive_interpolation
+
+
+def run_reconstruction(y: np.ndarray, cfa: str) -> np.ndarray:
+    """Performs demosaicking on y.
+
+    Args:
+        y (np.ndarray): Mosaicked image to be reconstructed.
+        cfa (str): Name of the CFA. Can be bayer or quad_bayer.
+
+    Returns:
+        np.ndarray: Demosaicked image.
+    """
+    current_directory = os.getcwd() #we take the current directory to be sure we will have the correct one
+    input_path='src/methods/domer/image-colorization/input/0.jpg'
+    input_path = os.path.join(current_directory, input_path)#location to store the image
+    output_path='src/methods/domer/image-colorization/output/0.jpg'
+    output_path = os.path.join(current_directory, output_path)
+    # venv_path='src/methods/domer/image-colorization/image-colorization/bin/activate'
+    # venv_path = os.path.join(current_directory, venv_path) #activation of the venv, but no need for a lot of versions of libraries
+    y2=Image.fromarray(y)
+    y2=y2.convert('L')
+    y2.save(input_path)
+    resolution=np.shape(y)[0]
+    # activation_venv = ['source ', venv_path]
+    # subprocess.run(activation_venv, shell=True)
+    n=y2.size[0]
+    # for i in range (n) :
+    #     for j in range (n) :
+    #         y2.putpixel((i,j),y.getpixel((i,j))*255)
+    command = [
+        'python', 'src/methods/domer/image-colorization/colorize.py',
+        '-i', input_path,
+        '-o', output_path,
+        '-r', str(resolution)
+    ]
+    subprocess.run(command) #calling of the NN with the location of the input and output and the resolution
+    # deactivation_venv = f"deactivate"
+    # subprocess.run(deactivation_venv, shell=True)
+    res=Image.open(output_path) #We take the result of the NN
+    res=np.asarray(res)#reseting the result in a numpy array
+
+    return res
+
+

src/methods/girardey/methods.py

+import numpy as np
+from src.forward_model import CFA
+
+def HQ_interpolation(op: CFA, y: np.ndarray) -> np.ndarray:
+    """Performs a simple interpolation of the lost pixels.
+
+    Args:
+        op (CFA): CFA operator.
+        y (np.ndarray): Mosaicked image.
+
+    Returns:
+        np.ndarray: Demosaicked image.
+    """
+    z = op.adjoint(y)
+
+    if op.cfa == 'bayer':
+        res = np.empty(op.input_shape)
+
+        res[:, :, 0] = varying_kernel_convolution_HQ(y[:, :], K_red_list)
+        res[:, :, 1] = varying_kernel_convolution_HQ(y[:, :], K_green_list)
+        res[:, :, 2] = varying_kernel_convolution_HQ(y[:, :], K_blue_list)
+ 
+    else:
+        res = np.empty(op.input_shape)
+
+        bayer_y = quad_bayer_to_bayer(y)
+        res[:, :, 0] = varying_kernel_convolution_HQ(bayer_y[:, :], K_red_list)
+        res[:, :, 1] = varying_kernel_convolution_HQ(bayer_y[:, :], K_green_list)
+        res[:, :, 2] = varying_kernel_convolution_HQ(bayer_y[:, :], K_blue_list)
+
+    return res
+
+def extract_padded(M, size, i, j):
+    N_i, N_j = M.shape
+    res = np.zeros((size, size))
+    middle_size = int((size - 1) / 2)
+
+    for ii in range(- middle_size, middle_size + 1):
+        for jj in range(- middle_size, middle_size + 1):
+            if i + ii >= 0 and i + ii < N_i and j + jj >= 0 and j + jj < N_j:
+                res[middle_size + ii, middle_size + jj] = M[i + ii, j + jj]
+
+    return res
+
+
+def varying_kernel_convolution(M, K_list):
+    N_i, N_j = M.shape
+    res = np.zeros_like(M)
+
+    for i in range(N_i):
+        for j in range(N_j):
+            res[i, j] = np.sum(extract_padded(M, K_list[4 * (i % 4) + j % 4].shape[0], i, j) * K_list[4 * (i % 4) + j % 4])
+
+    np.clip(res, 0, 1, res)
+
+    return res
+
+def varying_kernel_convolution_HQ(M, K_list):
+
+    res = np.zeros_like(M)
+    M_padded = np.pad(M,2,"constant",constant_values=0)
+    N_i, N_j = M_padded.shape
+    for i in range(2,N_i-2):
+        for j in range(2,N_j-2):
+            res[i-2, j-2] = np.sum(extract_padded(M_padded, 5, i ,j) * K_list[2* (i % 2) + j % 2])
+
+    np.clip(res, 0, 1, res)
+
+    return res
+
+def quad_bayer_to_bayer(y):
+    res = y
+    N_i, N_j = y.shape
+    for j in range(int(N_j/4)):
+        buff = res[:,j*4+1]
+        res[:,j*4+1] = res[:,j*4+2]
+        res[:,j*4+2] = buff
+    for i in range(int(N_i/4)):
+        buff = res[i*4+1,:]
+        res[i*4+1,:] = res[i*4+2,:]
+        res[i*4+2,:] = buff
+    for i in range(int(N_i/4)):
+        for j in range(int(N_j/4)):
+            buff = res[i*4+2,j*4+1]
+            res[i*4+2,j*4+1] = res[i*4+1,j*4+2]
+            res[i*4+1,j*4+2] = buff   
+    return res
+
+
+
+K_identity = np.zeros((5,5))
+K_identity[2,2] = 1
+
+K_g_r_and_b = np.array([[0, 0, -1, 0, 0], [0, 0, 2, 0, 0], [-1, 2, 4, 2, -1], [0, 0, 2, 0, 0], [0, 0, -1, 0, 0]]) / 8
+
+K_r_and_b_g_rrow_bcol = np.array([[0, 0, 1/2, 0, 0], [0, -1, 0, -1, 0], [-1, 4, 5, 4, -1], [0, -1, 0, -1, 0], [0, 0, 1/2, 0, 0]]) / 8
+K_r_and_b_g_brow_rcol = K_r_and_b_g_rrow_bcol.T
+K_r_b = np.array([[0, 0, -3/2, 0, 0], [0, 2, 0, 2, 0], [-3/2, 0, 6, 0, -3/2], [0, 2, 0, 2, 0], [0, 0, -3/2, 0, 0]]) / 8
+
+K_green_list = [K_identity, 
+                K_g_r_and_b,
+                K_g_r_and_b,
+                K_identity]
+
+K_red_list = [K_r_and_b_g_rrow_bcol,
+              K_identity,
+              K_r_b,
+              K_r_and_b_g_brow_rcol]
+
+K_blue_list = [K_r_and_b_g_brow_rcol,
+               K_r_b,
+               K_identity,
+               K_r_and_b_g_rrow_bcol]
\ No newline at end of file

src/methods/girardey/reconstruct.py

+
+import numpy as np
+
+from src.forward_model import CFA
+from src.methods.girardey.methods import HQ_interpolation
+
+
+def run_reconstruction_HQ(y: np.ndarray, cfa: str) -> np.ndarray:
+    """Performs demosaicking on y.
+
+    Args:
+        y (np.ndarray): Mosaicked image to be reconstructed.
+        cfa (str): Name of the CFA. Can be bayer or quad_bayer.
+
+    Returns:
+        np.ndarray: Demosaicked image.
+    """
+    input_shape = (y.shape[0], y.shape[1], 3)
+    op = CFA(cfa, input_shape)
+
+    res = HQ_interpolation(op, y)
+
+    return res

src/methods/khattabi/reconstruct.py

+"""The main file for the reconstruction.
+This file should NOT be modified except the body of the 'run_reconstruction' function.
+Students can call their functions (declared in others files of src/methods/your_name).
+"""
+
+
+import numpy as np
+
+from src.forward_model import CFA
+from src.methods.khattabi.utils import HA
+
+def run_reconstruction(y: np.ndarray, cfa: str) -> np.ndarray:
+    """Performs demosaicking on y.
+
+    Args:
+        y (np.ndarray): Mosaicked image to be reconstructed.
+        cfa (str): Name of the CFA. Can be bayer or quad_bayer.
+
+    Returns:
+        np.ndarray: Demosaicked image.
+    """
+    # Performing the reconstruction.
+    # TODO
+    input_shape = (y.shape[0], y.shape[1], 3)
+    op = CFA(cfa, input_shape)
+    y_adjoint=op.adjoint(y)
+    res = HA(y_adjoint)
+
+    return res
+
+
+####
+####
+####
+
+####      ####                ####        #############
+####      ######              ####      ##################
+####      ########            ####      ####################
+####      ##########          ####      ####        ########
+####      ############        ####      ####            ####
+####      ####  ########      ####      ####            ####
+####      ####    ########    ####      ####            ####
+####      ####      ########  ####      ####            ####
+####      ####  ##    ######  ####      ####          ######
+####      ####  ####      ##  ####      ####    ############
+####      ####  ######        ####      ####    ##########
+####      ####  ##########    ####      ####    ########
+####      ####      ########  ####      ####
+####      ####        ############      ####
+####      ####          ##########      ####
+####      ####            ########      ####
+####      ####              ######      ####
+
+# 2023
+# Authors: Mauro Dalla Mura and Matthieu Muller

src/methods/khattabi/utils.py

+"""A file containing a (pretty useless) reconstruction.
+It serves as example of how the project works.
+This file should NOT be modified.
+"""
+
+
+import numpy as np
+from scipy.signal import convolve2d
+
+from src.forward_model import CFA
+
+def HA(y_adjoint):
+    height, width = y_adjoint.shape[:2]
+    # Green channel interpolation
+
+
+    for i in range(2 , height-2): 
+        for j in range(2, width-2):
+            # Red pixels
+            if y_adjoint[i,j,1] == 0 and y_adjoint[i,j,0] != 0:  
+                grad_y = np.abs(y_adjoint[i-1,j,1] - y_adjoint[i+1,j,1]) + np.abs(2*y_adjoint[i,j,0] - y_adjoint[i-2,j,0] - y_adjoint[i+2,j,0])
+                grad_x = np.abs(y_adjoint[i,j-1,1] - y_adjoint[i,j+1,1]) + np.abs(2*y_adjoint[i,j,0] - y_adjoint[i,j-2,0] - y_adjoint[i,j+2,0])
+
+                if grad_x < grad_y:
+                    y_adjoint[i,j,1] = (y_adjoint[i,j-1,1] + y_adjoint[i,j+1,1])/2 + (2*y_adjoint[i,j,0] - y_adjoint[i,j-2,0] - y_adjoint[i,j+2,0])/4
+                elif  grad_x > grad_y:
+                    y_adjoint[i,j,1] = (y_adjoint[i-1,j,1] + y_adjoint[i+1,j,1])/2 + (2*y_adjoint[i,j,0] - y_adjoint[i-2,j,0] - y_adjoint[i+2,j,0])/4
+                else:
+                    y_adjoint[i,j,1] = (y_adjoint[i-1,j,1] + y_adjoint[i+1,j,1] + y_adjoint[i,j-1,1] + y_adjoint[i,j+1,1])/4 + \
+                                       (2*y_adjoint[i,j,0] - y_adjoint[i,j-2,0] - y_adjoint[i,j+2,0] + 2*y_adjoint[i,j,0] - y_adjoint[i-2,j,0] - y_adjoint[i+2,j,0])/8
+            # Blue Pixels
+            elif y_adjoint[i,j,1] == 0 and y_adjoint[i,j,2] != 0:   
+                grad_y = np.abs(y_adjoint[i-1,j,1] - y_adjoint[i+1,j,1]) + np.abs(2*y_adjoint[i,j,2] - y_adjoint[i-2,j,2] - y_adjoint[i+2,j,2])
+                grad_x = np.abs(y_adjoint[i,j-1,1] - y_adjoint[i,j+1,1]) + np.abs(2*y_adjoint[i,j,2] - y_adjoint[i,j-2,2] - y_adjoint[i,j+2,2])
+
+                if grad_x < grad_y:
+                    y_adjoint[i,j,1] = (y_adjoint[i,j-1,1] + y_adjoint[i,j+1,1])/2 + (2*y_adjoint[i,j,2] - y_adjoint[i,j-2,2] - y_adjoint[i,j+2,2])/4
+                elif  grad_x > grad_y:
+                    y_adjoint[i,j,1] = (y_adjoint[i-1,j,1] + y_adjoint[i+1,j,1])/2 + (2*y_adjoint[i,j,2] - y_adjoint[i-2,j,2] - y_adjoint[i+2,j,2])/4
+                else:
+                    y_adjoint[i,j,1] = (y_adjoint[i-1,j,1] + y_adjoint[i+1,j,1] + y_adjoint[i,j-1,1] + y_adjoint[i,j+1,1])/4 + \
+                                       (2*y_adjoint[i,j,2] - y_adjoint[i,j-2,2] - y_adjoint[i,j+2,2] + 2*y_adjoint[i,j,2] - y_adjoint[i-2,j,2] - y_adjoint[i+2,j,2])/8
+                    
+    # Red and blue channel interpolation
+    for i in range(1 , height-1):  
+        for j in range(1, width-1):
+            if y_adjoint[i,j,2] != 0 :
+                 y_adjoint[i,j,0] = (y_adjoint[i-1,j-1,0] + y_adjoint[i-1,j+1,0] + y_adjoint[i+1,j-1,0] + y_adjoint[i+1,j+1,0]) / 4
+
+            elif y_adjoint[i,j,0] != 0:
+                 y_adjoint[i,j,2] = (y_adjoint[i-1,j-1,2] + y_adjoint[i-1,j+1,2] + y_adjoint[i+1,j-1,2] + y_adjoint[i+1,j+1,2]) / 4
+            
+            else:
+                y_adjoint[i,j] = y_adjoint[i,j]
+
+    for i in range(1 , height-1):
+        for j in range(1, width-1):    
+            if y_adjoint[i,j,0] == y_adjoint[i,j,2]:
+                y_adjoint[i,j,0] = (y_adjoint[i-1,j,0] + y_adjoint[i,j-1,0] + y_adjoint[i+1,j,0] + y_adjoint[i,j+1,0]) / 4             
+                y_adjoint[i,j,2] = (y_adjoint[i-1,j,2] + y_adjoint[i,j-1,2] + y_adjoint[i+1,j,2] + y_adjoint[i,j+1,2]) / 4  
+            
+    return y_adjoint
+
+
+####
+####
+####
+
+####      ####                ####        #############
+####      ######              ####      ##################
+####      ########            ####      ####################
+####      ##########          ####      ####        ########
+####      ############        ####      ####            ####
+####      ####  ########      ####      ####            ####
+####      ####    ########    ####      ####            ####
+####      ####      ########  ####      ####            ####
+####      ####  ##    ######  ####      ####          ######
+####      ####  ####      ##  ####      ####    ############
+####      ####  ######        ####      ####    ##########
+####      ####  ##########    ####      ####    ########
+####      ####      ########  ####      ####
+####      ####        ############      ####
+####      ####          ##########      ####
+####      ####            ########      ####
+####      ####              ######      ####
+
+# 2023
+# Authors: Mauro Dalla Mura and Matthieu Muller