Lectures are held on Tuesdays and Thursdays from 1:30pm to 3:00pm @ Hewlett 201, also Zoom.
Recitations are held on select Fridays from 12:15pm to 1:15pm @ Building 200-230, also Zoom .
Students with Documented Disabilities: Students who may need an academic accommodation based on the impact of a disability must initiate the request with the Office of Accessible Education (OAE). Professional staff will evaluate the request with required documentation, recommend reasonable accommodations, and prepare an Accommodation Letter for faculty. Unless the student has a temporary disability, Accommodation letters are issued for the entire academic year. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations. The OAE is located at 563 Salvatierra Walk (phone: 723-1066, URL: https://oae.stanford.edu/).
Homework releases can be found on GitHub.
| Event Type | Date | Description | Pre-recorded Materials | Live Lecture Materials | |
|---|---|---|---|---|---|
| Lecture 1 |
Tuesday September 21 |
Course introduction and Logistics |
[1.1 What is Computer Vision]
[1.2 Computer Vision Applications] |
Logistics | |
| I. Low-Level Vision (this part will be flipped classroom) | |||||
| Lecture 2 |
Thursday September 23 |
Photometric Image Formation |
[2.1 Images, Sampling and Quantization]
[2.2 Color Physics] [2.3 Color Matching] [2.4 Color Constancy] |
Notebook
|
|
| Recitation 1 |
Friday September 24 |
Python/NumPy Review I |
|||
| Lecture 3 |
Tuesday September 28 |
Filters |
[3.1 Linear Systems]
[3.2 Convolution and Correlation] |
Notebook | |
| Lecture 4 |
Thursday September 30 |
Edges |
[4.1 Edge Detection Overview]
[4.2 Image gradients] [4.3 A simple edge detector] [4.4 Sobel edge detector] [4.5 Canny edge detector] [4.6 Hough Transform for Line Detection] |
Notebook | |
| Recitation 2 |
Friday October 1 |
Linear Algebra Review |
|||
| HW0 Due |
Friday October 1, 11:59pm |
Homework #0 due Basics |
[Homework #0] | ||
| Lecture 5 |
Tuesday October 5 |
Features and Matching |
[5.1 Ransac] [5.2 Local invariant features] [5.3 Harris Corner Detector] |
Notebook | |
| Lecture 6 |
Thursday October 7 |
Features and Matching |
[6.1 Scale invariant keypoint detection] [6.2 SIFT] [6.3 HoG] |
Notebook | |
| Recitation 3 |
Friday October 8 |
Panorama |
Slides | ||
| HW1 Due |
Friday October 8, 11:59pm |
Homework #1 due Filters |
[Homework #1] | ||
| Lecture 7 |
Tuesday October 12 |
Optical Flow |
[7.1 Optical Flow] [7.2 Lukas-Kanade method] [7.3 Pyramids for Large Motion] [7.4 Horn-Schunk method] [7.5 Applications] |
||
| II. Geometric Vision (this part will be live) | |||||
| Lecture 8 |
Thursday October 14 |
Geometric Image Formation [Why Geometric Vision Matters] [Geometric Primitives in 2D & 3D] [2D & 3D Transformations] |
Slides |
||
| Recitation 4 |
Friday October 15 |
Python/NumPy Review II |
|||
| HW2 Due |
Friday October 15, 11:59pm |
Homework #2 due Edge Detection |
[Homework #2] | ||
| Lecture 9 |
Tuesday October 19 |
Pinhole Camera Model [From 3D to 2D: the Pinhole Camera Model] [Properties of Perspective] [Monocular cues for 3D] |
Slides |
||
| Lecture 10 |
Thursday October 21 |
Camera Calibration [Camera Calibration: Estimating intrinsics K] [Pose Estimation: Estimating extrinsics [R|t]] |
Slides |
||
| HW3 Due |
Friday October 22, 11:59pm |
Homework #3 due Tracking/Flow |
[Homework #3] | ||
| Lecture 11 |
Tuesday October 26 |
Multi-view Geometry [Triangulation] [Epipolar geometry] [Stereo] |
Slides |
||
| Lecture 12 |
Thursday October 28 |
Structure from Motion [SfM Problem Definition] [Finding 2D Correspondences] [Solving for Cameras and 3D Points] |
Slides |
||
| HW4 Due |
Friday October 29, 11:59pm |
Homework #4 due Panorama Stitching |
[Homework #4] | ||
| III. Visual Pattern Recognition (this part will be live) | |||||
|
Tuesday November 2 |
No class (Stanford Democracy Day) |
||||
| Lecture 13 |
Thursday November 4 |
Segmentation |
[13.1 Introduction] [13.2 Gestalt theory] [13.3 Agglomerative clustering] [13.4 Oversegmentation] |
||
| HW5 Due |
Friday November 5, 11:59pm |
Homework #5 due Camera + Calibration |
[Homework #5] | ||
| Lecture 14 |
Tuesday November 9 |
Clustering |
[14.1 K-means] [14.2 Mean-shift] |
||
| Lecture 15 |
Thursday November 11 |
Supervised & Deep Learning |
[15.1 ML For CV: A Brief Overview] |
||
| IV. Advanced Topics (this part will be live) | |||||
| Lecture 16 |
Tuesday November 16 |
Understanding Videos |
[16 Understanding Videos] |
||
| Lecture 17 |
Thursday November 18 |
Vision for Robotics & Self-driving |
[17 Self-Supervised 3D Vision] |
||
|
Lecture 18 Guest Lecture by Vincent Sitzmann |
Tuesday November 30 |
Self-supervised Scene Representation Learning |
|||
|
Lecture 19 Guest Lecture by Anna Bethke |
Thursday December 2 |
The FATE of AI Ethics: How to research AI in a fair, accountable, transparent, explainable, and ethical manner |
|||
