CSE 527: Introduction to Computer
Vision
Fall
2023
Basic
Information:
¡¤ Lecture info: Mon/Wed 7:00pm ¨C 8:20pm, Frey Hall 102 (Map)
¡¤ Instructor: Haibin Ling (haibin.ling AT stonybrook.edu), NCS 147
¡¤ Office hour: Wed 3pm-5pm or by appointment
¡¤ TAs:
o Zihan Ding (Zihan.Ding AT stonybrook.edu), 3:00-5:00pm Thursday or by appointment
o Kalyan Garigapati (Kalyan.Garigapati AT stonybrook.edu), 7:00-9:00pm Thursday or by appointment
o Ruoyu Xue (ruoxue AT cs.stonybrook.edu), 1:15-3:15pm Wednesday or by appointment
¡¤ 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 8/28 8/30 |
¡¤ Introduction o Topics, history, applications, related fields o Course logistics ¡¤
Image Formation o Geometric primitives and transformations |
¡¤ Szeliski 1.1, 1.2 ¡¤ Szeliski 2.1, 2.2 |
Week 2 9/6 |
¡¤
Image Formation o Photometric image formation o Anatomy of cameras ¡¤
Tutorial to Google Colab
(By Kalyan Garigapati) ¡¤ Quiz 1 |
¡¤ Szeliski 2.2, 2.3 |
Week 3 9/11 9/13 |
¡¤
Image Formation (con¡¯t) o Photometric image formation o Anatomy of cameras ¡¤
Image Processing o Linear filtering: separable filtering o Non-linear filtering, bilateral filtering |
¡¤ Szeliski 2.2, 2.3 ¡¤ Szeliski 3.2, 3.3 |
Week 4 9/18 9/20 |
¡¤
Image Processing o Fourier transforms o Image pyramid o Geometric transform ¡¤
Model Fitting and Optimization o Line fitting, robust fitting o Hough transform o RANSAC |
¡¤ Szeliski 3.4, 3.5, 3.6 ¡¤ Szeliski 4.1 ¡¤ Szeliski 7.4, 8.1 |
Week 5 9/25 9/27 |
¡¤
Machine Learning o Supervised learning o Unsupervised learning ¡¤
Recognition o Instance recognition o Image classification (traditional methods) |
¡¤ Szeliski 5.1, 5.2 ¡¤ Szeliski 6.1, 6.2 |
10/1 |
¡¤
Homework 1 Due
(11:59pm EST) |
|
Week 6 10/2 10/4 |
¡¤
Deep Learning o Deep neural networks o Convolutional neural networks o Architecture o Applications ¡¤
Deep Learning Practice o Training o Data augmentation |
¡¤ Szeliski 5.3, 5.4, 5.5, 6.2 ¡¤ Deep Learning, Goodfellow et al., 2016. ¡¤ Deep Learning Tutorial, Stanford |
Week 7 10/11 |
Midterm |
|
Week 8 10/16 10/18 |
¡¤
Image classification o Vision Transformer ¡¤
Detection o Traditional solutions |
¡¤ Szeliski 5.5, 6.3 ¡¤ End-to-End Object Detection with Transformers, Carion, et al., ECCV 2020 |
Week 9 10/23 10/25 |
¡¤
Detection o Deep learning solutions ¡¤
Semantic Segmentation o Segmentation |
¡¤ Szeliski 6.3, 6.4 ¡¤ Segment Anything, Kirillov et al., 2023 |
10/29 |
Homework 2 Due (11:59pm EST) |
|
Week 10 10/30 11/1 |
¡¤
Semantic Segmentation o Segmentation o Semantic segmentation |
¡¤ Szeliski 6.3, 6.4 ¡¤ Segment Anything, Kirillov et al., 2023 |
Week 11 11/6 11/8 |
¡¤
Feature detection and matching o Points
and patches o Edges
and contours |
¡¤ Szeliski 7.1, 7.2, 7.5 |
Week 12 11/13 11/15 |
¡¤
Image alignment and stitching o Pairwise alignment o Image stitching o Global alignment ¡¤
Motion estimation and tracking o Translational alignment o Optical flow o Object tracking |
¡¤ Szeliski 8.1, 8.2, 8.3 ¡¤ Szeliski 9.1, 9.3, 9.4 |
Week 13 11/20 |
¡¤
Motion estimation and tracking o Object tracking |
¡¤ Szeliski 9.1, 9.3, 9.4 |
11/26 |
Homework 3 Due (11:59pm EST) |
|
Week 14 11/27 11/29 |
¡¤
Depth estimation o Epipolar geometry o Correspondences o Local and global methods o Deep learning solution ¡¤ Quiz 2 (11/29) |
¡¤ Szeliski 12.1, 12.2, 12.3, 12.4, 12.5, 12.6 |
Week 15 12/4 12/6 |
¡¤
Structure from motion and SLAM o Camera pose estimation o Two-frame structure from motion o Multi-frame structure from motion o Simultaneous localization & mapping (SLAM) ¡¤ Diffusion model for semantic segmentation (by Neelesh Verma, 12/6) ¡¤ Final review (12/6) |
¡¤ Szeliski 11.1, 11.2, 11.3, 11.4, 11.5 |
Week 16 12/11 |
¡¤
Advanced topic o Object pose estimation and application (by Ruyi Lian) |
|
12/17 |
Homework 4 Due (11:59pm EST) |
|
12/20 |
Final Exam, 5:30-8:00pm, Frey Hall 102 |
|