The University of Texas at DallasCS 6384: Computer Vision |
Spring 2024 |
|
Course Overview
Key Topics: Computer Vision, Deep Learning.
Description: This graduate-level computer vision course focuses on theory and practice of computer vision (CV). We will provide in-depth overview of CV, including image formulation, image filtering and transformation, feature detection and matching, modern neural networks, various recognition problems such as image classification, object detection, semantic segmentation, visual motion, 3D vision, and several advanced topics such as NeRF, visual representation learning, vision+language, and vision+audio.
Course Relevance: The course is relevant to students who want to understand and implement computer vision and deep learning techniques.
Course Goals: There are three primary course goals. First, the course aims to familiarize students with the fundamental concepts of image formulation, image processing, visual motion, classical feature detection and 3D vision. Second, the course helps students understand key components in modern deep learning-based computer vision. Third, through the assignments and final project, students have an opportunity to learn how to build practical computer vision systems.
Course Information
Instructor
Logistics
- Days & Times: Tuesday & Thursday 11:30AM - 12:45PM. Location: ECSW 1.365
- Prof. Tian's office hours: Tuesday 1:00PM – 2:00PM. Location: ECSS 4.211
- TA: Weiguo Pian. Office hours: Tuesday 4:30PM – 5:30 PM. Location: ECSS 4.222 Computer Vision and Multimodal Computing (CVMC) Lab
Assignment Structure
Students will be expected to:- Class participation (10%): Participate in class and take in-class quizzes.
- Homework Assignment (30%): Submit all homework assignments on time. Collaboration is allowed so long as final work is done independently, and all collaborators are acknowledged.
- Mindterm Exam (30%).
- Complete final (group) project (30%):
- Students will complete an independent project in groups of 2-4.
- Write-up reports.
- Present project in class.
Late Policy
For the assignments (not including your final project report), students will be allowed a total of five late days per semester. After you use up the free late days, your late submissions will be penalized as follows. Assignments turned in within 24 hours of the due date will receive 90% of its score. Assignments turned in within 48 hours of the due date will receive 70% of its score. Assignments more than 48 hours late will not be accepted.
Prerequisites
This course assumes familiarity with Linear Algebra and Python Programming. If you have not taken courses covering this material, consult with the instructor.