MSCV Program Curriculum

The MSCV program is a professional degree that prepares students for industry and a career related to computer vision. It is a full-time 16-month program, spanning three semesters and one summer. Students are required to complete 111 units to be eligible for graduation. The curriculum consists of four core courses (total of 39 units), three core options (36 units), and three electives (total of 36 units). Students must take three 12-unit courses in each semester. Since computer vision is a rapidly changing field, this course of study is subject to change in order to reflect state of the art updates.

Four core courses (fixed timing):
Semester #1: 16-820 Advanced Computer Vision
Semester #2: 16-621 MSCV Capstone
Summer: 16-991 B Internship (3 units)
Semester #3: 16-622 MSCV Capstone

Three core options (flexible timing):
10-601 Intro to ML OR 16-831 Intro to Robot Learning
15-663 Computational Photography OR 16-824 Visual Learning & Recognition
16-822 Geometry-based Methods in CV OR 16-833 Robot Localization & Mapping

Three electives (flexible timing):
Based on availability. There is a long pre-approved list below.

The core courses are designed to cover the necessary foundations in math, machine learning, and computer vision. Our goal is to address the two main areas of current computer vision systems (1) recognition (including images and videos, and web-based applications), and (2) geometry (including multi-view reconstruction, Web-scale reconstruction, SLAM). The electives offer a complement of specialized aspects of computer vision, together with further material on machine learning.

Students are required to complete 3 units of Internship during the summer in order to meet the 111-unit total for graduation. Summer internships must be relevant to computer vision. If unsure, students can gain approval from the MSCV Program Director. Students must register for 3 units of internship credit and will be required to submit a final report documenting the work that they completed during the internship. The MSCV faculty will review the final report and assign the student a pass/fail grade for his/her work. As an alternative to an internship, students may stay on campus to intern with a Professor.

  • MSCV Project I & II – 12 units each (24 units total) – Second and Third Semester

This program will include two project courses to facilitate the development of computer vision software. MSCV Project I & II will be offered in the second and third semesters. The project course will allow students to form small teams that will focus on a hands-on computer vision topic proposed by the course instructor, core faculty, or industry colleagues. Students may propose projects independently but they will have to be reviewed and approved by the core program faculty. All projects will be supervised and coordinated by the MSCV faculty. The project is intended to allow students to acquire hands-on experience and apply concepts and methods taught in class. Students will learn the challenges of real-world software development. The outcome of this course will be a final project report, coupled with a demonstration and presentation.

List of Courses:

Course Title

Course No.

Units

Electives (choose 3)

Vision Sensors 16-421 12
Learning-based Image Synthesis 16-726 12
Mechatronic Design 16-778 12
Mathematical Fundamentals for Robotics 16-811 12
Geometry-based Methods in Vision 16-822 12
Physics-based Methods in Vision 16-823 12
Visual Learning and Recognition 16-824 12
Learning for 3D Vision 16-825 12
Introduction to Robot Learning 16-831 12
Robot Localization and Mapping 16-833 12
Special Topics: Deep Reinforcement Learning for Robotics 16-881 12
Understanding and Critiquing Generative Computer Vision 16-895 12
Parallel Computer Architecture and Programming 15-618 12
Cloud Computing 15-619 12
Computer Graphics 15-662 12
Computational Photography 15-663 12
Physics-based Rendering 15-668 12
Graduate Artificial Intelligence 15-780 12
Multimedia Databases and Data Mining 15-826 12
Special Topics in Theory: Spectral Graph Theory 15-859N 12
Human Motion Modeling and Analysis 15-869 12
Planning, Execution, and Learning 15-887 12
Introduction to Machine Learning 10-601 12
Machine Learning with Large Datasets 10-605 12
Intermediate Deep Learning 10-617 12
Statistical Machine Learning 10-702 12
Deep Reinforcement Learning & Control 10-703 12
Topics in Deep Learning 10-707 12
Probabilistic Graphical Models 10-708 12
Deep Learning Systems: Algorithms and Implementation 10-714 12
Advanced Machine Learning: Theory and Methods 10-716 12
Convex Optimization 10-725 12
Machine Learning with Large Datasets 10-805/11-805 12
Natural Language Processing 11-611 12
Large Language Models: Methods & Applications 11-667 12
Large-Scale Multi-media Analysis 11-775 12
Multimodal Affective Computing 11-776 12
Advanced Multimodal Machine Learning 11-777 12
Intermediate Statistics 36-705 12
Advanced Statistical Theory I 36-755 12