EE 6485 Computer Vision 計算機視覺
Fall 2022, Mon. 17:30 to 18:20 and Wed. 16:30 to 18:20, Location DELTA台達215
Instructor: Min Sun
TAs: FuEn Wang (王福恩) fulton84717@gmail.com
Hank Liao (廖宏儒) hankliao87@gmail.com
Justin Li (李明峯) li871030@gmail.com
Chia-Wei Wu (吳家維) zxc775206@gmail.com
Course Description
Can computers understand the visual world as we could? This course treats vision as a process of inference from noisy and uncertain data and emphasizes probabilistic, statistical, data-driven approaches. Topics include image processing; segmentation, grouping, and boundary detection; recognition and detection; motion estimation and structure from motion. This class will also lead you to the discussion of applications applying state-of-the-art techbiques in recognition, detection, and video analysis.
The course will consist of four programming projects and one final gruop project (max 5 members each team). Please find information about final project in the syllabus.
Prerequisites
This course requires programming experience (mainly Python) as well as linear algebra, basic calculus, and basic probability. Previous knowledge of visual computing will be helpful.Textbook
Readings will be assigned in "Computer Vision: Algorithms and Applications" by Richard Szeliski. The book is available for free online or available for purchase.Resource
Awesome computer vision github linkAwesome deep learning github link
Grading
Your final grade will be made up from- 60% 4 programming projects
- 35% final projects (includes proposal, project pitch, midtern report, final project presentation, and final project report). 5 member each group maximum (Project Ideas)
- 5% class participation
Important Links
Contact Info and Office Hours
You can contact the professor with any of the following:- Min Sun: sunmin@ee.nthu.edu.tw
- Min Sun, Delta 962, Tel: 035731058, Time: Mon. 15:30 - 16:30 & Tue. 16:00 - 17:00
- TAs, EECS Building 711, Time: Wed. 20:00 - 21:00
Tentative Syllabus
Week | Class Dates | Topic | Slides | Recording | Extra Info (e.g., Homework/Exam) |
---|---|---|---|---|---|
1 | M, Sept. 12 | Intro. to computer vision (CV) | link | Policy form out | |
W, Sept. 14 | Camera Model, Light and color | link | Policy form due link Team form is out. |
||
Python tutorial | slides | Homework 1 (hybrid image) out link |
|||
2 | M, Sep. 19 | Image filtering | link | ||
W, Sep. 21 | Camera Geometry and calibration | pdf1,pdf2 | link,link | ||
3 | M, Sep. 26 | Single-view geometry | link | Final day to submit your team! intro | |
W, Sep. 28 | Holiday (Teachers' Day) | Homework 1 due Homework 2 out |
|||
4 | M, Oct. 3 | Epioplar geometry | link | ||
W, Oct. 5 | Stereo system | link | |||
5 | M, Oct. 10 | Holiday (National Day) | |||
W, Oct. 12 | Multi-view geometry | pdf1 pdf2 | link,link,link | Project proposal due | |
6 | M, Oct. 17 | Active strereo | link | ||
W, Oct. 19 | Fitting and matching | link,link | Homework 2 due | ||
7 | M, Oct. 24 | Colab and pytorch tutorial | link | ECCV-Trip | |
W, Oct. 26 | Project pitch (3-5 minutes, 20 team, 100 minutes) | ECCV-Trip | |||
8 | M, Oct. 31 | Intro. to machine learning | link | ||
W, Nov. 2 | Intro. to CNN-1 | link,link | Homework 3 out | ||
9 | M, Nov. 7 | Intro. to CNN-2 | link | ||
W, Nov. 9 | Training NN | link | |||
10 | M, Nov. 14 | Object Detection and Beyond | link | ||
W, Nov. 16 | Holiday (Sports Day) | Homework 3 due Homework 4 out |
|||
11 | M, Nov. 21 | Handle domain shift | link | Pre-recorded Lecture | |
W, Nov. 23 | Scaling-up Depth Estimation & Feature Tracking | link,link | Midterm project report due | ||
12 | M, Nov. 28 | Scaling-up Flow | link | ||
W, Nov. 30 | Neural Radiance Field (NeRF) | pdf1, pdf2 | link,link | ||
13 | M, Dec. 5 | Vision and language | link | ||
W, Dec. 7 | Guest Lecture of Video Anomaly Detection & Transformer in CV. | link,link | Homework 4 due. | ||
14 | M, Dec. 12 | Transformer in CV | link,link | ||
W, Dec. 14 | How to keep up with the advance in CV? | link,link | YOLO-v7 guest lecture at 1:30 pm. Location: Delta 919. | ||
15 | M, Dec. 19 | Final presentation | |||
W, Dec. 21 | Final presentation | ||||
16 | M, Dec. 26 | Final presentation | |||
W, Dec. 28 | Final presentation | ||||
17 | M, Jan. 2 | Holiday (New Year Day) | |||
W, Jan. 4 | Buffer | ||||
18 | M, Jan. 9 | Final exam week | |||
W, Jan. 11 | Final exam week | Final project report due |
Project Proposal Format:
- Max 4 pages;- 3 sections:
- Title and authors
- Sec 1. Intro: problem you want to solve and why
- Sec 2. Technical part: how do you propose to solve it?
- Sec 3. Milestones (dates and sub-goals)
- References
Project Progress (mid-term) Report Format:
- Max 4 pages;- 3 sections:
- Title and authors
- Sec 1. Intro: problem you want to solve and why
- Sec 2. Technical part: how do you propose to solve it?
- Sec 3. Milestones achieved so far
- Sec 4. Remaining milestones (dates and sub-goals)
- References
Project Final Report Format:
- Max 10 pages;- Title and authors
- Abstract: short summary of the project with main results
- 6 sections:
- Sec 1. Introduction: introduce the problem you want to solve, expain why it is important to solve it; and indicate the method you used to solve it. add a concept figure showing the overall idea behind the method you are presenting.
- Sec 2.1. Review of previous work (i.e. previous methods that have explored a similar problem)
- Sec 2.2. Say why your method is better than previous work; and/or summarize the key main contributions of your work;
- Sec 3.1: Technical part: Summary of the technical solution
- Sec 3.2: Technical part: Details of the technical solution; you may want to decompose this section into several subsections; add figures to help your explanation.
- Sec 4: Experiments: present here experimental results of the method you have implemented with plots, graphs, images and visualizations.
- Sec 5: Conclusions: what's the take home message?
- Sec 6: References
You can look at one of the recent publications (such as this) as an example.
Project Report Evaluation:
- Your project report will be evaluated based on the quality of the writing, the clarity of your technical explanation and, overall, how well you get your message across. If you follow the structure above, you'll have good chances to do a good job. :)Project Source Code:
There is no need to attach a print out of the source codes to the manuscript. Final source codes of your working program need to be shared with TA and the instructor through elearn; this file is due on the project submission due date.Project Pitch in Class:
- The presentation must be at most 5 minutes long. Please impress your audience with imaginary results to illustrate your idea.Project Presentation in Class:
- The presentation must be at most 15 minutes long. Please see below for detailed presentation guidelines.Presentation Format:
Your slides should consist of a title slide, followed by slides that discuss the following aspects of your project:- Problem Motivation/Description
- Technical Approach
- Some Results
Evaluation:
- Your team will be evaluated based on the clarity of the presentation, quality of the slides, how well you get your message across, and how well you handle the questions at the end. Note that the presentation can still contain ongoing/preliminary results; final results may be included in the final report.- We will use a peer-review system.