Introduction
to Computer Vision Spring 2021 |
Basic Information: · Lecture time: Mon/Wed 7:50pm – 9:10pm, online or NCS 120 · Instructor: Prof. Haibin Ling, hling AT cs.stonybrook.edu · Office hour: Tue 3pm-5pm · Syllabus: PDF · TAs: Heng Fan (hefan AT cs.stonybrook.edu):
3:30-5:30pm Monday Zuhui
Wang (zuhui.wang AT stonybrook.edu), office hour: 9-11am
Wednesday Pavani Tripathi (pavani.tripathi AT stonybrook.edu), by
appointment |
|
|
|
Special Note Spring 2021: 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 review posted slides, review
recorded lectures, seek notes from a classmate or identified class note taker,
write lab report 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. For questions or
more information click here.
Useful
Links:
· Computer Vision: Algorithms and Applications, Richard Szeliski, 2010.
· Computer Vision: Models, Learning, and Inference, Simon J.D. Prince, 2012.
Date |
Topics and Schedule (up to change) |
Material |
Week 1 |
SNOW, no class |
|
2/3 |
General introduction ·
Background ·
Topics and applications ·
Related fields ·
Milestones |
|
Week 2 |
Image formation ·
Basic facts about light ·
Anatomy of cameras ·
Matting |
Szeliski 2.1, esp.
2.1.5 |
2/10 |
Filters and
Noises ·
Modeling image noise ·
Convolution Brief tutorial to Google Colab (Pavani
Tripathi) |
Szeliski 3.1, 3.2,
3.3.1, 3.4 (Fourier Transforms) |
Week 3 |
Filters and
Noises ·
Smoothing images ·
Image pyramids
|
Szeliski 3.1, 3.2,
3.3.1, 3.4 (Fourier Transforms) |
2/17 |
Image Features ·
Point features ·
Corners and Edges ·
Scale ·
Orientation |
Szeliski 4.1.1, 4.1.2,
4.2 |
Week 4 |
Model Fitting ·
Lines, curves ·
Hough Transform |
Szeliski 4.1.3, 4.3.2 Szeliski 6.1, 2.1 |
2/24 |
·
Deformation ·
RANSAC |
|
2/27 |
Homework 1
due (11 :59pm EST)
|
|
Week 5 |
Perspective
Projection ·
Homogeneous coordinates |
Szeliski 2.1 |
3/3 |
·
Image warping |
|
Week 6 |
Multiple View
Geometry ·
Stereo viewing |
Szeliski 6.3.1, 7, 11 |
3/10 |
·
Stereo reconstruction |
|
Week 7 |
Object
Recognition ·
Overview of machine learning in computer vision ·
PCA for image patches |
|
3/17 |
·
Object representation ·
Classifiers ·
Object categories |
|
3/20 |
Homework 2
due (11 :59pm EST)
|
|
Week 8 |
·
Midterm review |
|
3/24 |
·
Midterm |
|
Week 9 |
Deep Learning ·
Deep neural networks ·
Convolutional neural networks |
· Deep Learning,
Goodfellow et al., 2016, MIT press. http://www.deeplearningbook.org/ |
3/31 |
·
Architectures ·
Applications |
· Deep Learning
Tutorial, http://ufldl.stanford.edu/tutorial/. |
Week 10 |
Deep Learning
Practice ·
Pre-training ·
Data-augmentation |
|
4/7 |
Illumination ·
Shading, shadows ·
Reflectance properties |
|
4/10 |
Homework 3
due (11 :59pm EST)
|
|
Week 11 |
Deep Generative
Models ·
Autoencoders, VAEs ·
Generative adversarial networks (GAN) |
|
4/14 |
Geometric Understanding in Deep Learning, Guest lecture by Prof. David Gu |
|
Week 12 |
Detection ·
Traditional solutions ·
Deep learning solutions |
|
4/21 |
·
Semantic segmentation |
|
4/24 |
Homework 4
due (11 :59pm EST)
|
|
Week 13 |
Motion & Tracking ·
Low level motion ·
Flow |
Szeliski 8.4 |
4/28 |
·
Recurrent neural networks Tracking in 2D and 3D |
|
Week 14 |
Advanced Topics
(up to change) ·
SLAM |
|
5/5 |
Spatial Augmented Reality – guest
lecture by Bingyao Huang |
|
5/8 |
Homework 5
due (11 :59pm EST)
|
|
|
|
|
Final exam |
|
|
|