Computer Vision Visuals
Classical image processing, geometry, detection, and vision architectures — taught through numbered SVG sequences
Camera Projection and Pinhole Model
How a 3D world maps to a 2D sensor using the pinhole model and similar triangles.
See it visuallyEdge Detection and Gradients
Discovering object boundaries by taking the derivative of an image using Sobel operators.
See it visuallyEpipolar Geometry
How two cameras constrain the search for matching 3D points down to a 1D line.
See it visuallyNon-Maximum Suppression (NMS)
How object detectors filter overlapping boxes to keep only the best predictions.
See it visuallyOptical Flow
Estimating the apparent motion of objects across consecutive video frames.
See it visuallyU-Net Segmentation
A neural network architecture that outputs pixel-wise classification maps.
See it visually