EECS 442: Computer Vision (Winter 2022)

This is the tentative schedule.

DateTopicMaterials
Thursday
January 6
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
Tuesday
January 11
Cameras 2
Intrinsics & Extrinsic Matrices, Lenses
Slides (PDF)
Slides (PPTX)
Reading: S2.1, H&Z 2, 6
Thursday
January 13
Math 1
Floating point numbers, Vector & Matrices
Slides (PDF)
Slides (PPTX)
Reading: Kolter
Things Don't Add Up
Using a Byte
Tuesday
January 18
Math 2
Eigenvectors and values, Singular Values, Derivatives
Reading: Kolter
Distance 3 Ways
Thursday
January 20
Light & Shading
Human Vision, Color Vision, Reflection
Slides (PDF)
Slides (PPTX)
Reading: S2.2, S2.3
Blind spot demo
Tuesday
January 25
Filtering
Linear Filters, Blurring, Separable Filters, Gradients
Slides (PDF)
Slides (PPTX)
Convolving Gracefully
Tuesday
January 25
Homework 0 Due

Thursday
January 27
Detectors & Descriptors 1
Edge Detection, Gaussian Derivatives, Harris Corners
Slides (PDF)
Slides (PPTX)
Multiscale Harris Corner Detection
Tuesday
February 1
Detectors & Descriptors 2
Scale-Space, Laplacian Blob Detection, SIFT
Slides (PDF)
Slides (PPTX)
Tuesday
February 1
Homework 1 Due

Thursday
February 3
Transforms 1
Linear Regression, Total Least Squares, RANSAC, Hough Transform
Slides (PDF)
Slides (PPTX)
Reading: S2.1, S6
Tuesday
Februrary 8
Transforms 2
Affine and Perspective Transforms, Fitting Transformations
Slides (PDF)
Slides (PPTX)
Reading: S2.1, S6
Grace in the Middle
Thursday
February 10
Machine Learning
Supervised Learning, Train/Val/Test Splits, Linear Regression, Regularization
Slides (PDF)
Slides (PPTX)
Reading: ESL 3.1, 3.2 (skim)
Tuesday
February15
Continuous Optimization
SGD, SGD+Momentum
Slides (PDF)
Slides (PPTX)
Thursday
February 17
Neural Networks
Backpropagation, Fully Connected Neural Networks
Slides (PDF)
Slides (PPTX)
Thursday
February 17
Homework 2 Due

Tuesday
February 22
Convolutional Networks 1
Convolution, Pooling
Slides (PDF)
Slides (PPTX)
Thursday
February 24
Convolutional Networks 2
CNN Architectures, Initialization, Augmentation, Transfer Learning
Slides (PDF)
Slides (PPTX)
Tuesday
March 1
Spring Break

Thursday
March 3
Spring Break

Tuesday
March 8
Segmentation
Semantic Segmentation
Slides (PDF)
Slides (PPTX)
Thursday
March 10
Detection and Other Problems
Detection, (a little) self-supervised learning
Slides (PDF)
Slides (PPTX)
Friday
March 11
Homework 3 Due

Tuesday
March 15
Image Synthesis and Other Problems
GANs, TBD
Slides (PDF)
Slides (PPTX)
Tuesday
March 15
Project Proposal Due

Thursday
March 17
Language & Transformers & Other Models
Transformers
Slides (PDF)
Slides (PPTX)
Tuesday
March 22
Ethics & Fairness
Fairness, Ethics
Slides (PDF)
Slides (PPTX)
Thursday
March 24
Optical Flow & Time
Optical Flow
Slides (PDF)
Slides (PPTX)
Reading: S8.4
Friday
March 25
Homework 4 Due

Tuesday
March 29
Camera Calibration
Intro to 3D, Camera Calibration
Slides (PDF)
Slides (PPTX)
Reading: S6.3
Thursday
March 31
Epipolar Geometry
Epipolar Geometry, The Fundamental & Essential Matrices
Slides (PDF)
Slides (PPTX)
Reading: S11
Tuesday
April 5
Stereo
Two-view Stereo, Multiview Stereo
Slides (PDF)
Slides (PPTX)
Reading: S11
Friday
April 8
Homework 5 Due

Thursday
April 7
Structure from Motion
Incremental/batch Structure from Motion
Slides (PDF)
Slides (PPTX)
Reading: S7
Tuesday
April 12
Single-View 3D
Perspective Invariants, Measuring Things
Slides (PDF)
Slides (PPTX)
Thursday
April 14
Learning 3D
Learning-Based 3D
Tuesday
April 19
Embodiment
Robotics and Embodiment
Tuesday
April 19
Homework 6 Due


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.

S is Computer Vision: Algorithms and Applications by Richard Szeliski, which can be found here.

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).

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