EECS 442: Computer Vision (Winter 2022)

Note: this is an archived webpage and is no longer in active use. I do not teach this course or any course at the University of Michigan anymore. I am preserving it in case it is useful for others.

S is Computer Vision: Algorithms and Applications by Richard Szeliski, which can be found here. The chapters refer to the first edition. This will be more accessible.

H&Z is Multiple View Geometry in Computer Vision by Richard Hartley and Andrew Zisserman, which can be obtained via the library in electronic form (scroll past the physical copies). I'd recommend this only if you're feeling adventerous.

ESL is Elements of Statistical Learning by Hastie, Tibshirani, and Friedman, which can be found here (PDF). This is relatively accessible.

Kolter is Zico Kolter's linear algebra review and reference note here (PDF). For the purpose of 442, feel free to skip ‘‘Determinants’’, ‘‘Quadratic Forms and Positive Semidefinite Matrices’’ (although this is good to know), ‘‘The Hessian’’, and ‘‘Gradients and Hessians of Quadratic and Linear Functions’’ (until we hit deep learning), and ‘‘Gradients of the Determinant’’.

DateTopicMaterials
Wednesday
January 4
Introduction + Cameras 1
Overview, Logistics, Pinhole Camera Model, Homogeneous Coordinates
Slides (PDF)
Slides (PPTX)
Reading: S2.1, H&Z 2, 6
Homogeneous Coordinates
Dolly Zoom on a Cube
Monday
January 9
Cameras 2
Intrinsics & Extrinsic Matrices, Lenses
Slides (PDF)
Slides (PPTX)
Reading: S2.1, H&Z 2, 6
Wednesday
January 11
Math Recap
Floating point numbers, Vector & Matrices, Eigenvectors and values, Singular Values, Derivatives
Slides (PDF)
Slides (PPTX)
Reading: Kolter
Things Don't Add Up
Using a Byte
Distance 3 Ways
Monday
January 16
No Class - Martin Luther King Day

Wednesday
January 18
Light & Shading
Human Vision, Color Vision, Reflection
Slides (PDF)
Slides (PPTX)
Reading: S2.2, S2.3
Monday
January 23
Filtering
Linear Filters, Blurring, Separable Filters, Gradients
Slides (PDF)
Slides (PPTX)
Convolving Gracefully
Wednesday
January 25
Homework 1 Due

Wednesday
January 25
Detectors & Descriptors 1
Edge Detection, Gaussian Derivatives, Harris Corners
Slides (PDF)
Slides (PPTX)
Multiscale Harris Corner Detection
Monday
January 30
Detectors & Descriptors 2
Scale-Space, Laplacian Blob Detection, SIFT
Slides (PDF)
Slides (PPTX)
Wednesday
February 1
Transforms 1
Linear Regression, Total Least Squares, RANSAC, Hough Transform
Slides (PDF)
Slides (PPTX)
Reading: S2.1, S6
Monday
February 6
Transforms 2
Affine and Perspective Transforms, Fitting Transformations
Slides (PDF)
Slides (PPTX)
Reading: S2.1, S6
Grace in the Middle
Wednesday
February 8
Homework 2 Due

Wednesday
February 8
Machine Learning
Supervised Learning, Train/Val/Test Splits, Linear Regression, Regularization
Slides (PDF)
Slides (PPTX)
Reading: ESL 3.1, 3.2 (skim)
Monday
February 13
Optimization
SGD, SGD+Momentum
Slides (PDF)
Slides (PPTX)
Wednesday
February 15
Neural Networks
Backprop, Fully Connected Neural Networks
Slides (PDF)
Slides (PPTX)
Monday
February 20
Convolutional Networks 1
Convolution, Pooling
Slides (PDF)
Slides (PPTX)
Wednesday
February 22
Homework 3 Due; Nope! March 6

Wednesday
February 22
Convolutional Networks 2
BatchNorm, CNN Architectures, Initialization, Augmentation, Transfer Learning
Slides (PDF)
Slides (PPTX)
Monday
February 27
Spring Break

Wednesday
March 1
Spring Break

Monday
March 6
Segmentation
Semantic/Instance Segmentation
Slides (PDF)
Slides (PPTX)
Wednesday
March 8
Detection & Other Topics
Detection, Other Stuff
Slides (PDF)
Slides (PPTX)
Monday
March 13
Image Synthesis

Slides (PDF)
Slides (PPTX)
Wednesday
March 15
Midterm

Monday
March 20
Project Proposal Due

Monday
March 20
Transformers & Other Models
Transformers, Other Models
Slides (PDF)
Slides (PPTX)
Wednesday
March 22
Camera Calibration
Intro to 3D, Camera Calibration
Slides (PDF)
Slides (PPTX)
Reading: S6.3
Monday
March 27
Single-View 3D
Perspective Invariants, Measuring Things
Slides (PDF)
Slides (PPTX)
Wednesday
March 29
Epipolar Geometry
Epipolar Geometry, The Fundamental & Essential Matrices
Slides (PDF)
Slides (PPTX)
Reading: S11
Friday
March 31
Homework 4 Due

Monday
April 3
Stereo
Two-view Stereo, Multiview Stereo
Slides (PDF)
Slides (PPTX)
Reading: S11
Wednesday
April 5
Structure from Motion
Incremental/batch Structure from Motion
Slides (PDF)
Slides (PPTX)
Reading: S7
Monday
April 10
Learning 3D
Learning-Based 3D
Wednesday
April 12
Ethics & Fairness
Fairness, Ethics
Slides (PDF)
Slides (PPTX)
Monday
April 17
Homework 5 Due

Monday
April 17
AI For Science
AI For Science


Re-use policy: I am extremely grateful to the many researchers who have made their slides and course materials available. Please feel to re-use any of my materials while crediting appropriately and making sure original attributions to these generous researchers is preserved. Please consider making your own course materials public.