2022 Faculty Courses School of Computing Department of Computer Science Graduate major in Artificial Intelligence
3D Computer Vision
- Academic unit or major
- Graduate major in Artificial Intelligence
- Instructor(s)
- Asako Kanezaki
- Class Format
- Lecture (HyFlex)
- Media-enhanced courses
- -
- Day of week/Period
(Classrooms) - 3-4 Tue (W833) / 3-4 Fri (S223)
- Class
- -
- Course Code
- ART.T466
- Number of credits
- 200
- Course offered
- 2022
- Offered quarter
- 4Q
- Syllabus updated
- Jul 10, 2025
- Language
- English
Syllabus
Course overview and goals
This course teaches how to process images and 3D data so as to extract higher-level information from the data. It covers the basics of data processing, geometric transformations, and linear algebra for machine learning, as well as recent cutting-edge research on deep neural networks, with hands-on exercises using programming languages such as Python.
Course description and aims
At the end of this course, students should be able to
1) acquire the basics of image and 3D data processing, and
2) implement their own desired processing including deep learning with e.g., Python.
Keywords
Image Processing, 3D Data Processing, Geometric Transformations, Deep Learning, Neural Networks
Competencies
- Specialist skills
- Intercultural skills
- Communication skills
- Critical thinking skills
- Practical and/or problem-solving skills
Class flow
This course will be taught with slides and programming exercises.
Course schedule/Objectives
| Course schedule | Objectives | |
|---|---|---|
| Class 1 | Input/Output of image and 3D data | Understand 3D sensors and how to input, output, and visualize data. |
| Class 2 | Image and 3D data pre-processing | Learn about data filtering and geometric transformations. |
| Class 3 | Image and 3D features | Learn about image features such as SIFT and 3D keypoints/local features. |
| Class 4 | Image and 3D data correspondence search | Learn about k-d tree data structure and nearest neighbor search |
| Class 5 | 3D data registration | Understand RANSAC and graph matching, and the ICP algorithm |
| Class 6 | Linear algebra as a basis for machine learning | Learn about linear algebra, the foundation of machine learning |
| Class 7 | Data classification using machine learning | Learn data classification techniques by support vector machines, etc. |
| Class 8 | Foundation of deep learning | Understand layers and the back propagation technique of deep learning |
| Class 9 | Image processing with deep learning (1) | Learn methods of image classification using deep learning |
| Class 10 | Image processing with deep learning (2) | Learn techniques such as image segmentation using deep learning |
| Class 11 | 3D data processing with deep learning (1) | Learn methods of 3D data classification using deep learning |
| Class 12 | 3D data processing with deep learning (2) | Learn techniques such as 3D data segmentation using deep learning |
| Class 13 | 3D data processing with deep learning (3) | Learn about 3D representations using implicit functions, machine learning using geometric information, etc. |
| Class 14 | Summary and Discussion | Summary and discussion of the lecture |
Study advice (preparation and review)
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
Textbook(s)
None
Reference books, course materials, etc.
Materials translated into English from the above-mentioned Japanese reference book will be distributed.
Evaluation methods and criteria
Comprehension of lecture content will be evaluated. Grades will be based on exercises and reports.
Related courses
- ART.T467 ： Fundamentals of Computer Vision
- ART.T552 ： Advanced Topics in Computer Vision
- ART.T551 ： Image and Video Recognition
Prerequisites
There are no prerequisites for this course.