File size: 9,180 Bytes
80bcac8 25e7739 80bcac8 f3aa2b6 80bcac8 f3aa2b6 80bcac8 f3aa2b6 80bcac8 f3aa2b6 80bcac8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | import { PaddingMode, ConvolutionStep, ImageDataExtended } from '@/types'
/**
* Computes a single convolution step for a specific pixel position.
* Useful for static visualization/inspection without running the full animation.
*/
export function computeConvolutionStep(
image: ImageDataExtended,
kernel: number[][],
padding: PaddingMode,
normalize: boolean,
x: number,
y: number,
channel: number
): ConvolutionStep {
const { width, height, channels } = image
const kernelSize = kernel.length
const halfKernel = Math.floor(kernelSize / 2)
const kernelSum = kernel.flat().reduce((a, b) => a + b, 0)
const normalizeFactor = normalize && kernelSum !== 0 ? 1 / kernelSum : 1
const inputPatch: number[][] = []
const multiplications: number[][] = []
let sum = 0
for (let ky = 0; ky < kernelSize; ky++) {
const patchRow: number[] = []
const multRow: number[] = []
for (let kx = 0; kx < kernelSize; kx++) {
const px = x + kx - halfKernel
const py = y + ky - halfKernel
const pixelValue = getPixel(image, px, py, channel, padding)
const kernelValue = kernel[ky][kx]
patchRow.push(pixelValue)
const mult = pixelValue * kernelValue
multRow.push(mult)
sum += mult
}
inputPatch.push(patchRow)
multiplications.push(multRow)
}
const outputValue = sum
const normalizedValue = sum * normalizeFactor
// Calculate progress (for consistency with generator)
const totalPixels = width * height * channels
const processedPixels = (y * width + x) * channels + channel + 1
const progress = processedPixels / totalPixels
return {
x,
y,
channel,
inputPatch,
kernel,
multiplications,
sum: outputValue,
outputValue: normalizedValue,
normalizedValue,
progress,
}
}
export function getPixel(
image: ImageDataExtended,
x: number,
y: number,
channel: number,
padding: PaddingMode
): number {
const { width, height, channels, data } = image
let px = x
let py = y
switch (padding) {
case 'zero':
if (px < 0 || px >= width || py < 0 || py >= height) return 0
break
case 'replicate':
px = Math.max(0, Math.min(px, width - 1))
py = Math.max(0, Math.min(py, height - 1))
break
case 'reflect':
if (px < 0) px = -px
if (px >= width) px = 2 * width - px - 2
if (py < 0) py = -py
if (py >= height) py = 2 * height - py - 2
px = Math.max(0, Math.min(px, width - 1))
py = Math.max(0, Math.min(py, height - 1))
break
case 'wrap':
px = ((px % width) + width) % width
py = ((py % height) + height) % height
break
}
const index = (py * width + px) * channels + channel
return data[index] / 255
}
export function setPixel(
image: ImageDataExtended,
x: number,
y: number,
channel: number,
value: number
): void {
const { width, channels, data } = image
if (x < 0 || x >= width || y < 0 || y >= image.height) return
const index = (y * width + x) * channels + channel
data[index] = Math.max(0, Math.min(255, Math.round(value * 255)))
}
export function* convolutionSteps(
image: ImageDataExtended,
kernel: number[][],
padding: PaddingMode,
normalize: boolean,
onProgress?: (progress: number) => void
): Generator<ConvolutionStep> {
const { width, height, channels } = image
const kernelSize = kernel.length
const halfKernel = Math.floor(kernelSize / 2)
const totalPixels = width * height * channels
let processedPixels = 0
const kernelSum = kernel.flat().reduce((a, b) => a + b, 0)
const normalizeFactor = normalize && kernelSum !== 0 ? 1 / kernelSum : 1
const outputData = new Float32Array(width * height * channels)
// For progressive rendering: yield partial output every N rows
const rowsPerYield = Math.max(1, Math.floor(height / 20)) // ~20 yields per image
let rowsSinceYield = 0
for (let y = 0; y < height; y++) {
for (let x = 0; x < width; x++) {
for (let c = 0; c < channels; c++) {
const inputPatch: number[][] = []
const multiplications: number[][] = []
let sum = 0
for (let ky = 0; ky < kernelSize; ky++) {
const patchRow: number[] = []
const multRow: number[] = []
for (let kx = 0; kx < kernelSize; kx++) {
const px = x + kx - halfKernel
const py = y + ky - halfKernel
const pixelValue = getPixel(image, px, py, c, padding)
const kernelValue = kernel[ky][kx]
patchRow.push(pixelValue)
const mult = pixelValue * kernelValue
multRow.push(mult)
sum += mult
}
inputPatch.push(patchRow)
multiplications.push(multRow)
}
const outputValue = sum
const normalizedValue = sum * normalizeFactor
const outputIndex = (y * width + x) * channels + c
outputData[outputIndex] = normalizedValue
processedPixels++
const progress = processedPixels / totalPixels
// Create partial output image for progressive rendering
let partialOutputImageData: ImageData | undefined
let isPartialOutput = false
if (c === channels - 1 && x === width - 1) {
// End of row - check if we should yield partial output
rowsSinceYield++
if (rowsSinceYield >= rowsPerYield || y === height - 1) {
// Create partial output image
const partialImageData = new ImageData(width, height)
for (let i = 0; i < outputData.length; i++) {
// Only fill up to current progress
const pixelIdx = Math.floor(i / channels)
const currentPixelIdx = y * width + x
if (pixelIdx <= currentPixelIdx) {
partialImageData.data[i] = Math.max(0, Math.min(255, Math.round(outputData[i] * 255)))
} else {
// Unprocessed pixels - show as transparent or original
partialImageData.data[i] = 0
partialImageData.data[i + 3] = 0 // transparent alpha for unprocessed
}
}
// Fill alpha for processed pixels
for (let py = 0; py <= y; py++) {
for (let px = 0; px < width; px++) {
for (let pc = 0; pc < channels; pc++) {
const idx = (py * width + px) * channels + pc
const imgIdx = (py * width + px) * 4 + pc
if (pc < 3) {
partialImageData.data[imgIdx] = Math.max(0, Math.min(255, Math.round(outputData[idx] * 255)))
} else {
partialImageData.data[imgIdx] = 255
}
}
}
}
partialOutputImageData = partialImageData
isPartialOutput = true
rowsSinceYield = 0
}
}
yield {
x,
y,
channel: c,
inputPatch,
kernel,
multiplications,
sum: outputValue,
outputValue: normalizedValue,
normalizedValue,
progress,
partialOutputImageData,
isPartialOutput,
}
if (onProgress) onProgress(progress)
}
}
}
// Convert output to ImageData
const outputImageData = new ImageData(width, height)
for (let i = 0; i < outputData.length; i++) {
outputImageData.data[i] = Math.max(0, Math.min(255, Math.round(outputData[i] * 255)))
}
// Final yield with complete output
yield {
x: -1,
y: -1,
channel: -1,
inputPatch: [],
kernel,
multiplications: [],
sum: 0,
outputValue: 0,
normalizedValue: 0,
progress: 1,
partialOutputImageData: outputImageData,
isPartialOutput: true,
}
}
export function convolveImage(
imageData: ImageData,
kernel: number[][],
padding: PaddingMode = 'zero',
normalize: boolean = true
): ImageData {
const extended: ImageDataExtended = {
data: imageData.data,
width: imageData.width,
height: imageData.height,
channels: 4,
}
const { width, height } = imageData
const kernelSize = kernel.length
const halfKernel = Math.floor(kernelSize / 2)
const kernelSum = kernel.flat().reduce((a, b) => a + b, 0)
const normalizeFactor = normalize && kernelSum !== 0 ? 1 / kernelSum : 1
const outputData = new Uint8ClampedArray(imageData.data.length)
for (let y = 0; y < height; y++) {
for (let x = 0; x < width; x++) {
for (let c = 0; c < 3; c++) {
let sum = 0
for (let ky = 0; ky < kernelSize; ky++) {
for (let kx = 0; kx < kernelSize; kx++) {
const px = x + kx - halfKernel
const py = y + ky - halfKernel
const pixelValue = getPixel(extended, px, py, c, padding)
sum += pixelValue * kernel[ky][kx]
}
}
const outputIndex = (y * width + x) * 4 + c
outputData[outputIndex] = Math.max(0, Math.min(255, Math.round(sum * normalizeFactor * 255)))
}
outputData[(y * width + x) * 4 + 3] = 255
}
}
return new ImageData(outputData, imageData.width, imageData.height)
} |