Textbook
[1] Richard Szeliski, Computer Vision: Algorithms and Applications, 2021.
Download
References
[1] Trevor Darrell's CS 280 Computer Vision class at Berkeley.
[2] Antonio Torralba's 6.869 Advances in Computer Vision class at MIT.
[3] Michael Black's CS 143Introduction to Computer Vision class at Brown.
[4] Kristen Grauman's CS 378 Computer Vision class at UT Austin.
[5] Alyosha Efros' 15-463 Computational Photography and 16-721 Learning-Based Methods in Vision classes at Carnegie Mellon.
GRADING
Homework (3 times) : 20%
Term Project : 30%
Midterm Exam : 20%
Final Exam : 30%
Absent : -3 total score each time (Roll call is not taken in every week.)
Announcement
請負責報告的同學提前一到兩天把PPT寄給助教。並請上課時，自備筆電。
| • 視訊連結: |
Link
| • Term Project |
| 投影片: Link |
| Proposal: 1 page |
| CVGIP 2026 template: Link |
Course Links
Youtube
Handouts (2021 ~ ) (PPT Format)
Chapter 1a: Introduction |
2026
Chapter 1b: Introduction (including HW1) |
2026
Chapter 2: Image Formation (including HW2) |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 3: Image Processing |
2021 |
2022 |
2023 |
2024 |
2025 |
2026 |
Chapter 4: Model Fitting and Optimization |
2021 |
2022 |
2023 |
2024 |
2025 |
2026 |
Chapter 5: Deep Learning |
2021 |
2022 |
2023 |
2024 |
2025 |
2026 |
Chapter 6: Recognition |
2021 |
2022 |
2023 |
2024 |
2025 |
2026 |
Chapter 7: Feature Detection and Matching |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 8: Image Alignment and Stiching |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 9: Motion Estimation (including HW3) |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 10: Computational Photography |
2021 |
2022 |
2023 |
2024 |
2025 |
2026 |
Chapter 11: Structure from Motion and SLAM |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 12: Depth Estimation |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 13: 3D Reconstruction |
2021 |
2022 |
2023 |
2024 |
2025 |
2026
Chapter 14: Image-Based Rendering |
2021 |
2022 |
2024 |
2025 |
2026
Research
03/03 PCB X-ray Images Restoration Based on NAFNet
03/10 research progress Paulo Linares
03/17 ALPR
04/05 PetStream_report
04/05 Mediapipe
04/28 superframe
04/28 Colon Anatomy Localization
05/05 Ternary Quantization for Large Language Models
05/11 Permanent Magnet Identification
05/11 The Research of Deep Learning for Recognizing Lane Change Violations
05/18 Subpixel Edge Detection
05/25 3D Face Reconstruction
05/25 An Efficient YOLO Model for PCB Defect Detection
Late homeworks will be subjected to grade penalties! Please compress the homework files to a zip file. The filename format is [STUDENT-ID]_HW[HW-NUMBER].zip
(e.g. R07922666_HW1.zip).
HomeWork File Format and Content:
[STUDENT-ID]_HW[HW-NUMBER].zip
|---[STUDENT-ID]_HW[HW-NUMBER]
|--------[STUDENT-ID]_report [.pdf]
|--------[STUDENT-ID]_code [.py, .cpp ....]
Late homeworks will be subjected to grade penalties (20% off) .
Submissions more than three days late will not be graded.
Only electronic submissions are allowed! The homework should include two parts, the report and source code. Report formats are restricted to Adobe PDF format. Failure to fulfill the file formats when submitting your homework will result with no grades. Also, please take note of the fields for submission.
Your homework report should include the following contents: a brief discription of your homework, the algorithm you used, your parameters (if any), your principal code fragment, and the resulting images (please paste the images in your report file).
Do not copy homeworks from others. Copying is cheating, and cheating is shameful. You and the person who let you copy his/her homework will both get a 0. In addition, you could be subjected to an on site demostration for the following assignments.
Any programming language are allowed to used for homework. Do not use any library except basic I/O function (e.g. read file, write file, show image).
