Schedule
Texbooks
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 is available from the UM Library (Login required).
ESL is Elements of Statistical Learning by Hastie, Tibshirani, and Friedman, which can be found here
Event | Date | Description | Course Materials |
---|---|---|---|
Lecture 1 | Tuesday January 19 |
Introduction
Computer vision overview Course logistics Pinhole camera Homogenous coordinates |
[Intro slides (pdf)]
[Intro slides (pptx)] [Camera slides (pdf)] [Camera slides (pptx)] [video] |
Lecture 2 | Thursday January 21 |
Cameras II
Intrinsic / Extrinsic matrices Thin lens model Depth of field |
[slides (pdf)]
[slides (pptx)] [video] [Reading: S 2.1] [Reading: H&Z 2, 6] [Homogeneous coordinates notebook] [Rendering a cube/dolly zoom notebook] |
Lecture 3 | Tuesday January 26 |
Light and Shading
Human vision Color vision Color spaces Diffuse and Specular Reflection |
[slides (pdf)]
[slides (pptx)] [video] [Reading: S2.2, S2.3] |
Lecture 4 | Thursday January 28 |
Math Review
Floating point numbers Vectors, matrices Eigenvalues, Eigenvectors Least Squares Singular Values Derivatives |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 5 | Tuesday February 2 |
Filtering
Linear filters Blur and sharpening filters Separable filters Image gradients |
[slides (pdf)]
[slides (pptx)] [video] [Convolving Gracefully notebook] |
HW0 Due | Wednesday February 3 |
Homework 0 Due | [HW0] |
Lecture 6 | Thursday February 4 |
Detectors and Descriptors I
Edge detection Gaussian Derivative filter Harris Corner detector |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 7 | Tuesday February 9 |
Detectors and Descriptors II
Scale-space pyramid Laplacian blob detectors SIFT descriptors |
[slides (pdf)]
[slides (pptx)] [video] [Multiscale Harris Detector notebook] |
HW1 Due | Wednesday February 10 |
Homework 1 Due | [HW1] |
Lecture 8 | Thursday February 11 |
Transformations I
Linear Regression Total Linear Regression RANSAC Hough Transform |
[slides (pdf)]
[slides (pptx)] [video] [Reading: S2.1, S6] |
Lecture 9 | Tuesday February 16 |
Transformations II
Affine, Projective transforms Fitting transforms |
[slides (pdf)]
[slides (pptx)] [video] [Reading: S2.1, S6] |
Lecture 10 | Thursday February 18 |
Machine Learning
Image warping / blending Supervised vs Unsupervised learning Train / Test splits Linear Regression Regularization |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 11 | Tuesday February 23 |
Linear Models
Cross-Validation K-Nearest Neighbors SVM loss Cross-Entropy loss |
[slides (pdf)]
[slides (pptx)] [video] [CS231n Linear Classification] |
Well-Being Day | Thursday February 25 |
No Class: Well-Being Day | |
HW2 Due | Friday February 26 |
Homework 2 Due | [HW2] |
Lecture 12 | Tuesday March 2 |
Optimization
Stochastic Gradient Descent SGD + Momentum |
[slides (pdf)]
[slides (pptx)] [video] [CS231n Optimization] |
Lecture 13 | Thursday March 4 |
Neural Networks
Overfitting / Underfitting Bias / Variance tradeoff Fully-connected neural networks Biological neurons |
[slides (pdf)]
[slides (pptx)] [video] [CS231n Neural Networks] |
Lecture 14 | Tuesday March 9 |
Backpropagation
Computational Graphs Backpropagation Matrix multiplication example |
[slides (pdf)]
[slides (pptx)] [video] [231n Backpropagation] [Backprop for Matrix Multiply] [Olah on Backprop] [Nielsen on Backprop] |
HW3 Due | Wednesday March 10 |
Homework 3 Due | [HW3] |
Lecture 15 | Thursday March 11 |
Convolutional Networks I
Convolution Pooling |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 16 | Tuesday March 16 |
Convolutional Networks II
Batch Normalization CNN Architectures Weight initialization Data augmentation Transfer learning |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 17 | Thursday March 18 |
Segmentation and Detection
Semantic Segmentation Instance Segmentation Two-Stage Detectors Single-Stage Detectors |
[slides (pdf)]
[slides (pptx)] [video] |
Tuesday March 23 |
No Class: Well-Being Day | ||
Lecture 18 | Thursday March 25 |
Fairness in AI |
[slides (pdf)]
[slides (pptx)] [video] |
HW4 Due | Monday March 29 |
Homework 4 Due | [HW4] |
Lecture 19 | Tuesday March 30 |
Optical Flow |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 20 | Thursday April 1 |
3D Vision + Calibration |
[slides (pdf)]
[slides (pptx)] [video] |
Proposal Due | Monday April 5 |
Project Proposal due | [Proposal Details] |
Lecture 21 | Tuesday April 6 |
Single-View Geometry |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 22 | Thursday April 8 |
Epipolar Geometry |
[slides (pdf)]
[slides (pptx)] [video] |
HW5 Due | Friday April 9 |
Homework 5 Due | [HW5] |
Lecture 23 | Tuesday April 13 |
Stereo Vision |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 24 | Thursday April 15 |
Structure from Motion |
[slides (pdf)]
[slides (pptx)] [video] |
Lecture 25 | Tuesday April 20 |
Applications: Learning-Based 3D | [video] |
HW6 Not Due | Tuesday April 20 |
Homework 6 Due | [HW6] |
Tuesday April 27 |
Final Project Due (Showcase + Report) | [Info (pdf)] |