We will have 6 homework assignments, which will be listed below as they are assigned. The assignments will be given out every week starting week 2.
Note that there is a deadline for each assignment. Anything uploaded after the deadline will be marked late. Please be careful to not overwrite an in time assignment with a late assignment when uploading near the deadline.
Each student has four penalty-free late days for the whole quarter; other than that any late submission will be penalized for each day it is late.
Please let the TA know if you cannot access any of the pages.
- Homework 0: Fun with color!, due April 5th at midnight
- Homework 1: Resizing and convolutions, due April 12th at midnight
- Homework 2: Panoramas!, due April 26th at midnight
- Homework 3: Optical Flow, due May 3rd at midnight
- Homework 4: Neural Networks and Machine Learning, due May 10th at midnight
- Homework 5: PyTorch, due May 17th at midnight
Turn in all homeworks on canvas.
There will be a final project worth 20% of your final grade. The project can be done individually or in teams. We will have a poster session in the CSE Atrium June 6th, 4:30-6:30pm.
Pick any area of computer vision that interests you and pursue some independent work in that area. Each project should have a significant technical component, software implementation, or large-scale study. Projects can focus on developing new techniques or tools in computer vision or applying existing tools to a new domain. If you don't have an idea you can train a classifier on birds and compete in the Kaggle competition posted on the Google Group.
For your poster you can use Kiana's template here. If you send your poster using the template by Sunday night we can print them for the poster session. Otherwise, feel free to make your own poster, print it, and assemble it for the poster session! You can find the grading rubric for the final project here.
- Lecture: Introduction
- Lecture: Human Vision, Color Spaces and Transforms
- Optional reading: Computer Vision - 2.3.2 Color
- Other resources: Computer Vision A Modern Approach - 3 Color
- A painter's take on vision and color (very extensive!): Color Vision
- Lecture: Image coordinates, resizing
- Lecture: Resizing, filters, convolutions
- Optional reading: Computer Vision: A Modern Approach - 7 Linear Filters and Convolution
- Lecture: Edges and features
- Lecture: Harris, matching, RANSAC
- Lecture: Matching, RANSAC, HOG, SIFT
- Lecture: Optical Flow
- Lecture: 3D, Depth Perception, and Stereo
- Lecture: Machine Learning
- Lecture: More Machine Learning for Computer Vision
- Happy May Day!
- Lecture: Neural Networks
- Lecture: Convolutional Neural Networks
- Lecture: Network Architectures
- Tutorial: PyTorch
- Lecture: Semantic Segmentation
- Lecture: Object Detection
- Guest Lecture from Ira Kemelmacher-Shlizerman
- Lecture: Detection and Instance Segmentation
- Lecture: Vision and Language
- Lecture: Generative Adversarial Networks
- Optional: Computer Vision: Algorithms and Applications Rick Szeliski, 2010.
The final grade will consist of homeworks (80%) and a final project (20%)
Course Administration and Policies
- Collaboration is encouraged! Feel free to discuss howemork and class material with other students. However, make sure you understand the concepts. Each student will complete and submit their own work. Do not directly or indirectly copy other students' work.
- If you are working together or helping another student, work on teaching them concepts and answering general questions, not directly telling them what code to write. You're all smart; you should understand the line between productive collaboration and giving someone answers.
- Each student has four penalty-free late day for the whole quarter. Beyond that, late submissions are penalized.
- Comments can be sent to the instructor or TA using this anonymous feedback form here. We take all feedback very seriously and will do whatever we can to address any concerns.