Introduction to Computer Vision

Part 1: Classical 2D Image Processing

• Lesson 1: Images as Arrays
• Lesson 2: Image Arithmetic
• Lesson 3: Thresholding, Erosion, and Dilation
• Lesson 4: Flood Fill and Connected Components
• Lesson 5: Image Moments
• Lesson 6: Eigenvectors and Eigenvalues of the Covariance Matrix
• Lesson 7: Distance Measures
• Lesson 8: Geometric Transformations
• Lesson 9: Image Warping, Inverse Mapping, and Bilinear Interpolation
• Lesson 10: Convolution
• Lesson 11: Smoothing and Gaussian Pyramids
• Lesson 12: Differentiation and Edge Detection
• Lesson 13: Second Derivatives and the Laplacian
• Lesson 14: Nonlinear Filters
• Lesson 15: The Fourier Transform and Frequency-Domain Filtering
• Lesson 16: Wavelets and Gabor Filters
• Lesson 17: Image Compression – Lossless and Lossy
• Lesson 18: Color Spaces

Part 2: Classical 3D Computer Vision

• Lesson 19: Feature Detection and Matching
• Lesson 20: Optical Flow and Motion Estimation
• Lesson 21: Stereo Matching
• Lesson 22: Model Fitting, Robust Estimation, and RANSAC
• Lesson 23: Projective Geometry
• Lesson 24: Image Stitching and Mosaicking
• Lesson 25: Image Formation
• Lesson 26: Epipolar Geometry
• Lesson 27: Camera Calibration
• Lesson 28: Structure from Motion

Part 3: Deep Learning for Computer Vision

• Lesson 29: Projection – The Central Idea
• Lesson 30: Neural Network Fundamentals – Learning the Projection
• Lesson 31: Multi-Layer Perceptrons – Composing Projections
• Lesson 32: Optimization
• Lesson 33: Convolutional Neural Networks
• Lesson 34: Training a CNN
• Lesson 35: Classic Architectures
• Lesson 36: Transfer Learning
• Lesson 37: Image Classification in Practice
• Lesson 38: Visualizing and Understanding CNNs
• Lesson 39: Object Detection I – Sliding Windows, from Rowley-Baluja-Kanade to Viola-Jones
• Lesson 40: Object Detection II – From Classification to Regression
• Lesson 41: Semantic Segmentation
• Lesson 42: Instance Segmentation

Part 4: Transformers and Foundation Models

• Lesson 44: The Attention Mechanism
• Lesson 45: The Transformer Architecture
• Lesson 46: Vision Transformers (ViT)
• Lesson 47: Self-Supervised and Contrastive Learning
• Lesson 48: DINOv2 and Self-Distillation
• Lesson 49: Vision-Language Models
• Lesson 50: Visual Question Answering
• Lesson 51: Segment Anything
• Lesson 52: Open-Vocabulary Detection
• Lesson 53: Monocular Depth Estimation
• Lesson 54: Depth Anything
• Lesson 55: Stereo Depth and FoundationStereo
• Lesson 56: Feed-Forward Camera Pose Estimation
• Lesson 57: Generative and Diffusion Models
• Lesson 58: Neural Rendering

References