CSE 327: Fundamentals of Computer Vision

(Undergraduate Course)

Fall 2024

Basic Information:

· Lecture info: Mon/Wed 3:30pm – 4:50pm, Frey Hall 205

· Instructor: Haibin Ling (haibin.ling AT stonybrook.edu), NCS 147

· Office hour: Wed 9:30am-11:30am or by appointment

· TAs:

o Ming Lin, ming.lin@stonybrook.edu, office hour: Mon 9:30-11:30am

o Shivasankaran Vanaja Pandi, shivasankaran.vanajapandi@stonybrook.edu, office hour: Tue 9-11am

o Naman Joshi, namjoshi@cs.stonybrook.edu, office hour: Thu 12-2pm

o Rushil Nilesh Shah, rushshah@cs.stonybrook.edu, office hour: Mon 3-5pm

· Syllabus: PDF

Useful Links:

· Main textbook: Computer Vision: Algorithms and Applications, Richard Szeliski, 2nd ed., 2022.

· Computer Vision: A Modern Approach, David Forsyth and Jean Ponce, 2nd ed., 2012.

· Multiple View Geometry in Computer Vision, Richard Hartley and Andrew Zisserman, 2nd ed., 2004.

· Pattern Recognition and Machine Learning, Christopher M. Bishop, 2006.

· Monocular Model-Based 3D Tracking of Rigid Objects: A Survey, Vincent Lepetit, Pascal Fua, 2005.

Course Schedule (tentative, will be actively updated during semester)

Date	Topics	Materials
Week 1 8/26 8/28	· Introduction o Topics, history, applications, related fields o Course logistics · Image Formation o Camera anatomy o Anatomy of cameras	· Szeliski 1.1, 1.2 · Szeliski 2.1, 2.2, 2.2, 2.3
Week 2 9/4	· Review of math and coding (by Kalyan Garigapati) o Basic math concept review o Tutorial to Google Colab
Week 3 9/9 9/11	· Image Formation o Photometric image formation · Image Processing o Point operations o Filters, convolution o Fourier transformation · Quiz 1 (9/11)	· Szeliski 2.1, 2.2, 2.2, 2.3 · Szeliski 3.1-3.4
Week 4 9/16 9/18	· Image Processing o Image smoothing o Histogram equalization o Image pyramid o Geometric transform o Image gradient o Points, corners, edges o Scale and orientation	· Szeliski 3.4, 3.5, 3.6 · Szeliski 7.1, 7.2, 7.4, 7.4
Week 5 9/23 9/25	· Model Fitting and Optimization o Line fitting, robust fitting o Hough transform o RANSAC	· Szeliski 4.1, 4.2 · Szeliski 7.4, 8.1
9/29	· Homework 1 Due (11:59pm EST)
Week 6 9/30 10/2	· Machine Learning Concepts o Supervised learning o Unsupervised learning · Quiz 2 (10/2)
Week 7 10/7 10/9	· Elements of perspective geometry o Homogeneous coordinates o Camera geometry transformations o Epipolar geometry	· Szeliski 5.5, 6.3
Week 8 10/16	· Stereo o Stereo viewing
10/20	Homework 2 Due (11:59pm EST)
Week 9 10/21 10/23	· Midterm (10/21) · Stereo o Stereo reconstruction	· Szeliski 12.1, 12.2, 12.3, 12.4, 12.5, 12.6 ·
Week 10 10/28 11/30	· Motion estimation and tracking o Translational alignment o Optical flow	· Szeliski 9.1, 9.3
Week 11 11/4 11/6	· Recognition o Instance recognition o Image classification (traditional methods) · Deep Learning o Deep neural networks	· Szeliski 5.3, 5.4, 5.5, 6.2 · Deep Learning, Goodfellow et al., 2016. · Deep Learning Tutorial, Stanford
11/10	Homework 3 Due (11:59pm EST)
Week 12 11/11 11/13	· Deep Learning o Convolutional neural networks o Architecture · Deep Learning Practice o Training o Data augmentation	· Szeliski 8.1, 8.2, 8.3
Week 13 11/18 11/20	· Detection and segmentation o Traditional solution o Deep learning solutions o Semantic segmentation · Quiz 3 (11/18)	· Szeliski 6.3, 6.4 · End-to-End Object Detection with Transformers, Carion, et al., 2020 · Segment Anything, Kirillov et al., 2023
11/24	Homework 4 Due (11:59pm EST)
Week 14 11/25	· Vision Transformer o Transformer o Transformer in computer vision	· Szeliski 5.5
Week 15 12/2 12/4	· Video analytics o Video object tracking o Activity understanding · Guest lecture by Peiyao Wang (12/4) o Temporal Action Segmentation · Quiz 4 (12/4)	· Szeliski 9.4
Week 16 12/9	· Advanced topic o Generative models · Final review
12/10	Homework 5 Due (11:59pm EST)
12/16	Final Exam, 5:30-8:00pm, Frey Hall 205