Computer Vision
CSCI/EENG/ROBO 437/507/517
Computer Vision | Colorado School of Mines
Welcome to the course website for Computer Vision. This site is the main entry point for course information, lecture material, schedules, and resources.
Course Material
Course Information
Syllabus
Course policies, grading, learning objectives, and resources.
Schedule
Lecture topics, homework deadlines, exams, and important dates.
Teaching Assistants
TA contact information, office hours, and locations.
Learning Materials
Lectures
Interactive lecture slides and downloadable PDF versions.
Assignments
Homework assignments and supporting files.
Tutorials
Tutorials for tools and software used in the course.
About the Course
The course covers both classical and modern computer vision, including:
- Image formation and image processing
- Filtering, convolution, and Fourier analysis
- Feature detection and matching
- Camera geometry and calibration
- Stereo vision, motion, and 3D reconstruction
- Image classification and object detection
- Deep learning and convolutional neural networks
- Practical computer vision using Python, OpenCV, and PyTorch
Course at a Glance
| Instructor | Kaveh Fathian |
| Semester | Fall 2026 |
| Class | Monday & Wednesday, 3:00–4:15 PM |
| Location | CoorsTek 130 |
| Programming | Python |
| Primary Communication | Ed Discussion |
Course Website vs. GitHub Repository
This website is the primary place to browse the course: syllabus, schedule, TA information, lectures, and other course resources.
The GitHub repository contains the downloadable files, code, notebooks, and other source material used in the course.
Acknowledgments and Use
These course materials build significantly on slides and teaching materials developed by other instructors, especially James Tompkin, Srinath Sridhar, Phillip Isola, William Freeman, Antonio Torralba, Kris Kitani, Takeo Kanade, Matthew O’Toole, and Chen Wang.
You are welcome to use and adapt these materials for academic, educational, or research purposes. If you reuse or redistribute them, please retain all acknowledgments and attributions to the original authors and sources. Some figures, examples, and other third-party materials may be subject to their own licenses or usage terms; please respect those requirements when reusing them.