CAP6412 – Spring 2023
Advanced Computer Vision (3 Credit Hours)
Instructor: | Dr. Mubarak Shah |
Email: | shah@crcv.ucf.edu |
Office: | HEC 245 |
Phone: | 407-823-5077 |
Time: | Monday and Wednesdays 3:00 to 4:15PM |
Location: | Zoom |
Schedule: | HTML |
Office Hours: | Mondays 2:00 to 3:00PM; Wednesdays 4:15 to 5:00PM; Fridays 1:00 to 2:00pm; and by appointment |
Course Content
This is an Advanced Computer Vision course which will expose graduate students to the cutting-edge research in Computer Vision. We will discuss research papers on diffusion models and their applications to image synthesis, super-resolution, object detection, inpainting, etc.
Computer vision has been very active area of research for many decades and researchers have been working on solving important challenging problems. During the last few years, Deep Learning involving Artificial Neural Networks has been disruptive force in computer vision. Employing deep learning, tremendous progress has been made in a very short time in solving difficult problems and very impressive results have obtained in image and video classification, localization, semantic segmentation, etc. New techniques, datasets, hardware, and software libraries are emerging almost every day. Deep Computer vision is impacting research in Robotics, Natural Language understanding, Computer Graphics, multi-modal analysis etc. One of the most important and impactful works during the last decade has been GAN (Generator Adversarial Network), which has enabled researchers to produce very realistic images and videos. Recently, very different approach employing diffusion models have been proposed, through which high quality and high-resolution images have been generated which are even better than images generated by GAN. The basic idea in diffusion models is to gradually diffuse an image by adding random noise, such that all information in the image is removed and it becomes a pure noise. This process is called forward diffusion. In the backward diffusion, a noisy image is gradually de-noised such that it becomes a realistic image. A neural network is trained employing samples from training distribution to estimate the noise or parameters of noise distribution. During inference (backward process) new realistic looking images can be generated by sampling this distribution. This course will focus on diffusion models.
Grading Policy
- Reports (you have to do only 50% of the papers): 15%
- Presentation(roughly two): 25%
- Attendance: 10%
- Projects: 50%
Late Policy
- 0 for late Reports
- 20% off per day, up to 4 days, for Presentations/Projects
Student Learning Outcomes
After the completion of the course, the students should be able to:
- Read and understand a research paper.
- Write a comprehensive review of the paper.
- To identify strong and weak points of the papers.
- To generate own ideas to solve the same problem.
- To work on research project and write a research paper
-
Review/rehearsal of power point presentation meeting:
-
- For Monday presentation
- Slide Review: Wednesday 4:15 a week before the scheduled presentation
- Rehearsal: Friday a week before the scheduled presentation 1:00PM during Office hours
- For Wednesday presentation
- Slide Review : A week before the scheduled presentation : Friday 1:00PM during Office hours
- Rehearsal: A week of presentation on Monday 2:00PM during Office hours
- For Monday presentation
Important Dates:
See https://calendar.ucf.edu/2023/spring
Statement on Academic Integrity:
The UCF Golden Rule will be observed in the class. Plagiarism and Cheating of any kind on an examination, quiz, or assignment will result at least in an “F” for that assignment (and may, depending on the severity of the case, lead to an “F” for the entire course) and may be subject to appropriate referral to the Office of Student Conduct for further action. I will assume for this course that you will adhere to the academic creed of this University and will maintain the highest standards of academic integrity. In other words, don’t cheat by giving answers to others or taking them from anyone else. I will also adhere to the highest standards of academic integrity, so please do not ask me to change (or expect me to change) your grade illegitimately or to bend or break rules for one person that will not apply to everyone.