CSE 527: Introduction to Computer Vision

(Graduate Course)

Spring 2022

Basic Information:

Special Note Spring 2022: Students are expected to attend every class, report for examinations and submit major graded coursework as scheduled. If a student is unable to attend lecture(s), report for any exams or complete major graded coursework as scheduled due to extenuating circumstances, the student must contact the instructor as soon as possible. Students may be requested to provide documentation to support their absence and/or may be referred to the Student Support Team for assistance. Students will be provided reasonable accommodations for missed exams, assignments or projects due to significant illness, tragedy or other personal emergencies. In the instance of missed lectures or labs, the student is responsible for reviewing posted slides, reviewing recorded lectures, seeking notes from a classmate or identified class note taker, writing lab reports based on sample data. Please note, all students must follow Stony Brook, local, state and Centers for Disease Control and Prevention (CDC) guidelines to reduce the risk of transmission of COVID.

Useful Links:
Date Lecture Topics (tentative schedule) Materials (for references)
Week 1
1/24
1/26 		General Introuction
  • Background, topics, applications, related fields
  • Course logistics
Image formation
  • Baisc facts about light
  • Anatomy of cameras
  • Matting
  • Szeliski 1.1, 1.2
  • Szeliski 2.1, 2.2, 2.3
Week 2
1/31
2/2 		Filters and noises
  • Point operators
  • Image filters, Fourier transforms
  • Szeliski 3.1, 3.2, 3.3
Week 3
2/7
2/9 		Filters and noises
  • Smoothing images
  • Image pyramid
Tutorial to Google Colab (By Kalyan Garigapati)
Image features
  • Points, corners, edges
  • Scale and orientation
  • Szeliski 3.3, 3.4, 3.5, 3.6
  • Szeliski 7.1, 7.2
Week 4
2/14
2/16 		Model Fitting
  • Lines and curves
  • Hough transform
  • Deformation
  • RANSAC
  • Szeliski 4.1, 7.4, 8.1
2/20 Homework 1 due (11:59pm EST)
Week 5
2/21
2/23 		Perspective Projection
  • Homogeneous coordinates
  • Image warping
  • Szeliski 2.1, 8.1, 8.2
Week 6
2/28
3/2 		Multiple View Geometry
  • Stereo viewing
  • Stereo reconstruction
  • Szeliski 12.1, 12.2, 12.3, 12.5
Week 7
3/7
3/9 		Object Recognition
  • Machine learning overview
  • PCA for image patches
  • Object representation
  • Classifiers and category recognition
  • Szeliski 5.1, 5.2, 6.1, 6.2
3/14 Homework 2 due (11:59pm EST)
Spring Break
Week 8
3/21
3/23 		Object Recognition
  • Machine learning overview
  • PCA for image patches
  • Object representation
  • Classifiers and category recognition
Midterm Review

Midterm (3/23)
  • Szeliski 5.1, 5.2, 6.1, 6.2
Week 9
3/28
3/30 		Deep Learning
  • Deep neural networks
  • Convolutional neural networks
  • Architecture
  • Applications
Week 10
4/4
4/6 		Deep Learning Practice
  • Training
  • Data augmentation
  • Szeliski 5.3, 5.4, 5.5, 2.2
4/10 Homework 3 due (11:59pm EST)
Week 11
4/11
4/13 		Deep Generative Models
  • Autoenvoders, VAEs
  • Generative adversarial networks (GAN)
  • Szeliski 5.5
Week 12
4/18
4/20		 Detection and segmentation
  • Traditional solutions
  • Deep learning solutions
  • Semantic segmentation
  • Szeliski 6.3, 6.4
4/24 Homework 4 due (11:59pm EST)
Week 13
4/25
4/27		 Motion and Tracking
  • Low level motion and optical flow
  • Recurrent neural networks
  • Object tracking
  • Szeliski 9.3, 9.4
Week 14
5/2
5/4		 Advanced Topics
  • Visual SLAM
  • Spatial augmented reality
  • Szeliski 11
5/9 Homework 5 due (11:59pm EST)
5/17 Final Exam, Tuesday 5/17, 5:30pm-8:00pm EST, in-person at LTENGR 102 and NCS 120