Learn

The blog lists everything by date. These two arrange the same articles by what you need first, so you can read straight down instead of guessing where to start.

Computer Vision Fundamentals

Imaging, image processing, features, geometry. 29 articles, ordered by dependency: nothing appears before the thing it depends on.

F1

Imaging

How light becomes an array of numbers.

How a scene is flattened onto a sensor, and what the glass does on the way.

  1. 1 The pinhole model
  2. 2 Lenses and depth of field
  3. 3 Lens distortion
  4. 4 Wide-angle and fisheye

What the number in a pixel counts, and how far it can be trusted.

  1. 1 From photons to counts
  2. 2 Noise and dynamic range
  3. 3 The response curve
  4. 4 High dynamic range
  5. 5 Sensing colour: the Bayer CFA

What the array holds, where its samples sit, how finely they are written, and what the file did to them.

  1. 1 An image is an array
  2. 2 Sampling: the pixel grid
  3. 3 Quantization and bit depth
  4. 4 Colour spaces
  5. 5 How close is your colour?
  6. 6 File formats and compression
F2

Image processing

What you do to that array once you have it.

2.1 Spatial filtering

The one operation behind blur, sharpening, edges and every CNN.

  1. 1 How 2D convolution works
F3

Features

What in an image is worth pointing at, and how to describe it.

3.3 SIFT

Surviving a camera that moves: scale space, and 128 numbers per point.

  1. 1 What makes a point matchable?
3.5 Alignment and outliers

Fitting a model when most of the correspondences are wrong.

  1. 1 RANSAC
F4

Geometry

From one camera to many, and back out to three dimensions.

4.1 Camera geometry

Intrinsics, extrinsics, calibration, and pose from known points.

  1. 1 Camera models, calibration and PnP
4.3 Many views

Recovering structure and motion from a set of photographs.

  1. 1 Structure from motion

Model and edge-deployment articles have no reading order in the same way, since each one is a benchmark that stands alone, so they live on the blog.