Understand the 3D world from 2D images
Course Information
Term: Spring 2025
Class Level: Undergraduate
Activity Type: Lecture
Days & Times: Tuesday & Thursday 11:30 AM – 12:45 PM
Location: ECSS 2.311
Instructor: Prof. Yu Xiang
Office Location: ECSS 4.702
Office Hours: Tuesday & Thursday 2:00PM – 3:00PM
Teaching Assistant: Jishnu P
Office Hours: Monday 12:00PM – 1:00PM
Course Description
Theory and practice of computer vision. Provides in-depth overview of computer vision, including geometric primitives and transformations, camera models, image features, epipolar geometry and stereo, structure from motion and SLAM, 3D reconstruction, variations of modern neural networks and various recognition problems such as object detection, semantic segmentation, and human pose estimation.
Textbooks
Richard Szeliski. Computer Vision: Algorithms and Applications. 2011th Edition. Springer.
ISBN-13: 978-1848829343
ISBN-10: 1848829345
Second Edition
David Forsyth, Jean Ponce. Computer Vision: A Modern Approach, 2nd Edition. Pearson, 2011. (Optional)
ISBN: 9789332550117
Richard Hartley. Multiple View Geometry in Computer Vision, 2nd Edition. Cambridge University Press, 2004. (Optional)
ISBN-13: 978-0521540513
ISBN-10: 0521540518
Grading Policy
- Homework (50%)
- Assignment 1 (10%)
- Assignment 2 (10%)
- Assignment 3 (10%)
- Assignment 4 (10%)
- Assignment 5 (10%)
- Midterm Exam (20%)
- Final Exam (25%)
- In-Class Activity (5%)
Homework
- Assignment 1
- Assignment 2
- Assignment 3
- Assignment 4
- Assignment 5
Learning from the “Cracker Box”
Lectures
| Date | Topic |
| Week 1, 1/21, Lecture 1 | Introduction to Computer Vision |
| Week 1, 1/23, Lecture 2 | Intensity Surface and Gradients |
| Week 2, 1/28, Lecture 3 | Image Filtering and Convolution |
| Week 2, 1/30, Lecture 4 | Smoothing |
| Week 3, 2/4, Lecture 5 | Edge Detection |
| Week 3, 2/6, Lecture 6 | Corner Detection |
| Week 4, 2/11, Lecture 7 | Laplacian and Blob Detection |
| Week 4, 2/13, Lecture 8 | Scale Invariance and SIFT I |
| Week 5, 2/18, Lecture 9 | Scale Invariance and SIFT II |
| Week 5, 2/20, Lecture 10 | Geometric Primitives and Transformations |
| Week 6, 2/25, Lecture 11 | Camera Projection |
| Week 6, 2/27, Lecture 12 | Camera Calibration |
| Week 7, 3/4, Lecture 13 | Epipolar Geometry |
| Week 7, 3/6 | Midterm Exam |
| Week 8, 3/11, Lecture 14 | Epipolar Geometry and Stereo |
| Week 8, 3/13, Lecture 15 | Structure from Motion I |
| Week 9, 3/18 | Spring Break |
| Week 9, 3/20 | Spring Break |
| Week 10, 3/25, Lecture 16 | Structure from Motion II |
| Week 10, 3/27, Lecture 17 | Convolution Neural Networks I |
| Week 11, 4/1, Lecture 18 | Convolution Neural Networks II |
| Week 11, 4/3, Lecture 19 | Convolution Neural Networks III |
| Week 12, 4/8, Lecture 20 | Recurrent Neural Networks I |
| Week 12, 4/10, Lecture 21 | Recurrent Neural Networks II |
| Week 13, 4/15, Lecture 22 | Transformer I |
| Week 13, 4/17, Lecture 23 | Transformer II |
| Week 14, 4/22, Lecture 24 | Object Detection I |
| Week, 14, 4/24, Lecture 25 | Object Detection II |
| Week 15, 4/29, Lecture 26 | Semantic Segmentation I |
| Week 15, 5/1, Lecture 27 | Semantic Segmentation II |
| Week 16, 5/6, Lecture 28 | Semantic Segmentation II |
| Week 16, 5/8 | Final Exam |