Programmiererforum

Code: Select all

// Convert image to tensor data
const imageToTensor = async (imageBuffer, rFactor) => {
// const img = new Image();
// img.src = imageBuffer;

const imageSharp = sharp(imageBuffer); // Create a sharp instance
// Get metadata (includes width and height)
const metadata = await imageSharp.metadata();

// Get original dimensions and LAB values
const originalLab = await imageSharp.toColorspace('lab').raw().toBuffer();

// First convert to grayscale using sharp for better preprocessing
const grayscaleBuffer = await imageSharp
.grayscale()
.resize(rFactor, rFactor, {
fit: 'fill',
kernel: 'lanczos3', // Use better quality resizing
})
.raw()
.toBuffer();

// Prepare tensor data with proper normalization
const tensorData = new Float32Array(3 * rFactor * rFactor);
for (let i = 0; i < grayscaleBuffer.length; i++) {
// Normalize to 0-1 range
const normalizedValue = grayscaleBuffer[i] / 255.0;

// Fill all three channels with the same normalized value
tensorData[i] = normalizedValue;
tensorData[i + rFactor * rFactor] = normalizedValue;
tensorData[i + 2 * rFactor * rFactor] = normalizedValue;
}

return {
originalLab,
tensorData,
dimensions: { width: metadata.width, height: metadata.height },
};
};

//colorizedData is output from onnx model

async function colorizeImage(inputImageBuffer, colorizedData, dimensions) {
try {
// Convert original image to LAB to extract L channel
const originalLab = await sharp(inputImageBuffer)
.toColorspace('lab')
.raw()
.toBuffer();

// Create buffer for final image
const finalImageBuffer = Buffer.alloc(
dimensions.width * dimensions.height * 3
);

// 3. Combine channels:
// - Use L (luminance) from original image
// - Use a,b (color) channels from colorized result
for (let i = 0; i < dimensions.width * dimensions.height; i++) {
const idx = i * 3;

// Copy L channel from original image
finalImageBuffer[idx] = originalLab[idx];

// Copy a,b channels from colorized result, with enhanced color saturation
finalImageBuffer[idx + 1] = colorizedData[idx + 1] * 1.3; // Enhance 'a' channel
finalImageBuffer[idx + 2] = colorizedData[idx + 2] * 1.3; // Enhance 'b' channel
}

// 4.  Create final image with enhanced processing pipeline
const finalImage = await sharp(finalImageBuffer, {
raw: {
width: dimensions.width,
height: dimensions.height,
channels: 3,
},
})
.toColorspace('lab')
// Apply multi-stage processing
//.blur(6.5) // Initial blur to reduce artifacts
//.gamma(1.1) // Slight gamma adjustment for better contrast
.modulate({
// Fine-tune color saturation
saturation: 1, //how "pure" a color appears versus how "washed out" or gray it looks.
//Increasing brightness makes an image look lighter (closer to white), while decreasing it makes it darker (closer to black)
brightness: 1.85, // Increase brightness by 85%
})
.toColorspace('srgb') // Convert back to RGB
.jpeg({
quality: 100,
chromaSubsampling: '4:4:4', // Preserve color quality
trellisQuantisation: true, // Enable trellis quantization for better quality
overshootDeringing: true, // Reduce ringing artifacts
optimizeScans: true, // optimizeProgressive scans
})
.toBuffer();

return finalImage;
} catch (error) {
console.error('Error in colorization post-processing:', error);
throw error;
}
}

Code: Select all

    def colorize(self, image, r_factor):

# Preprocess image:
# - Convert to LAB, extract L channel, convert back to RGB
targetL = cv2.cvtColor(image,cv2.COLOR_BGR2LAB)
targetL,_,_=cv2.split(image)

image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image = cv2.cvtColor(image, cv2.COLOR_GRAY2RGB)

# Resize, convert to float32, transpose, and add batch dimension
h, w, channels = image.shape

image = cv2.resize(image,(r_factor, r_factor))
image = image.astype(np.float32)
image = image.transpose((2, 0, 1))
image = np.expand_dims(image, axis=0).astype(np.float32)

# run deoldify:
colorized = self.session.run(None, {(self.session.get_inputs()[0].name):image})[0][0]
print(colorized)
# Postprocess image:
# - Transpose, convert BGR to RGB, resize, apply Gaussian blur
# - Convert back to LAB, split channels, resize
# - Merge L from original, A and B from colorized, convert back to BGR
colorized = colorized.transpose(1,2,0)
colorized = cv2.cvtColor(colorized, cv2.COLOR_BGR2RGB).astype(np.uint8)
colorized = cv2.resize(colorized,(w,h))
colorized = cv2.GaussianBlur(colorized,(13,13),0)
colorizedLAB = cv2.cvtColor(colorized,cv2.COLOR_BGR2LAB)
L,A,B=cv2.split(colorizedLAB)
colorizedLAB = cv2.resize(colorizedLAB,(w, h))
colorized = cv2.merge((targetL,A,B))
colorized = cv2.cvtColor(colorized,cv2.COLOR_LAB2BGR)

return colorized