Blur, sharpen, and edge detection all come from one operation: sliding a small matrix over an image. It is also the exact operation a CNN learns.
Image Convolution / KernelsLive
the operation inside every CNN
Controls
Presets
3×3 kernel
-1
-1
-1
-1
8
-1
-1
-1
-1
Each output pixel is a weighted sum of its 3×3 neighborhood. Slide this kernel over an image and you get blur, sharpening, or edge maps — the exact operation a convolutional neural network learns.
Reading this result: Convolution slides the 3-tap kernel over the image; each output pixel is a weighted sum of its 3×3 neighbors. At sigma ≈ 0.4 the weights stay tightly concentrated, so edges and fine detail survive and high-frequency structure is preserved.
Runs locally in your browser — free forever. Scale to the cloud when reality gets heavy.
★ Sign in to save this setupSave your tuned setup, or drop this simulation into your own site, docs, or course page.
How it works
Convolution replaces each pixel with a weighted sum of its neighbors, where the weights form a small kernel matrix. Different kernels produce blurring, sharpening, embossing, or edge maps. Convolutional neural networks work by learning these kernels from data instead of hand-picking them.
✦
Ask the AI about this model
The math, the assumptions, real-world uses, or a code translation — explained for this exact simulation.
Is this image convolution kernel tool really free?▾
Yes. Image Convolution / Kernels runs entirely in your browser using your device's own compute, so local use is free forever. You only pay Compute Tokens if you scale a job to the cloud.
Do I need to install anything?▾
No. Everything runs client-side in a modern browser — no downloads, no license, no account required to start.
Can I save or share my simulation?▾
Create a free account to save projects, and use a shareable embed or minted DOI to publish a live, interactive version anywhere.
How accurate are the results?▾
The solver uses established numerical methods, but results are for research and educational purposes and should be validated against experiment or professional review before you rely on them.