COMP 790-175
Visual Computing Systems
Fall 2025
COMP 790-175
COMP 790-175
Course Description
This graduate-level seminar explores recent advances in visual computing systems, with a strong emphasis on computational imaging. Topics include light transport modeling, computational imaging tasks and sensors, opto-electronic system design, and inverse problems in imaging.
While the course emphasizes theoretical foundations, we will also connect these ideas to emerging developments in generative AI and their applications in visual computing. We will devote the first few classes to introductory lectures. The remainder of the semester will focus on student-led paper presentations and discussions. Students will also undertake a semester-long research project.
Target Audience
Masters and PhD students interested in computational cameras, computational displays, graphics, imaging systems and visual computing.
Learning Objectives & Outcomes
By the end of this course, you will be able to:
- •Critically read, analyze, and discuss research papers
- •Improve technical presentation and communication skills
- •Understand the core concepts of computational imaging systems
- •Model and simulate optical/imaging systems
- •Develop mathematical models for light transport and visual computing
- •Gain hands-on programming and research skills through projects
Instructor
Prof. Praneeth Chakravarthula
Department of Computer Science
Email: praneeth@cs.unc.edu
Office Hours: By appointment only (SN 205 or Zoom)
Course Logistics
Meeting Times
Lectures: Tuesday/Thursday, 11:00am-12:15pm
Location: FB141
Course Communication
Course Site: Canvas and/or course website
Slides: Posted on Canvas and course website
Presentation Schedule: Available on course website
Course Materials
Study Materials
- Primary: Slides and additional readings posted on Canvas and/or course website
- Foundation: First principles of computer vision video lecture series (required viewing during first 3 weeks)
- Reference: Siggraph example review form for paper reviews
Programming Requirements
Students are expected to be comfortable with:
- Python (preferred)
- PyTorch/TensorFlow
- MATLAB
Coursework
Grade Distribution
Seminar Format
Each student will present 1-2 papers during the semester. Before each class, all students must read the assigned papers and submit a written review (format provided by the instructor).
Class Structure
- • The instructor provides an overview of the research topic and paper
- • The assigned student presents a 20-minute detailed technical analysis, followed by discussion and Q&A
- • Students are divided into two groups, arguing for acceptance vs. rejection of the paper based on its merits and limitations
- • Active participation is expected in discussions and debates. Attendance will be recorded for each session
Final Project (50%)
All students will write a “mini-paper” as a final project. The paper should extend one or more papers covered in class. Students should write code and carry out additional experiments and then write up the results in a standard conference paper format.
Project Guidelines
- • Students welcome to work in groups (2-4 people recommended)
- • Maximum paper length: 3 + n_students pages (not including references or contributions paragraph)
- • Project proposal due by start of class on October 14th
- • Final presentations during final exam period - all group members must present
Attendance & Late Work Policy
If you miss a class without completing the corresponding assignment, you’ll get a zero for that session. There’s no way to accept late work for readings since it’s vital that we’re all reading the same papers at the same time.
Final project cannot be accepted after the scheduled final exam slot since you need to present it then.
Schedule & Topics
Foundations
Aug 21, Thurs: Linear algebra recap
Aug 28, Thurs: Image recovery and inverse problems
Sep 4, Thurs: No class
Coded and Computational Cameras
Sep 11, Thurs: Deep optics
High-Dimensional Imaging
Sep 18, Thurs: DiffuserCam: lensless single-exposure 3D imaging
Single-Photon Imaging
Sep 25, Thurs: Quanta burst photography
Computational Light Transport
Oct 2, Thurs: Recovering 3D shape around the corner using ultrafast time-of-flight imaging
Mid-term Project Proposals
Oct 9, Thurs: Project proposals and presentations
Weeks 9-16: Advanced Topics
- • Unconventional Imaging and Sensing (Week 9)
- • Neural Rendering and Gaussian Splatting (Week 10)
- • Neural Representations and Computational Imaging I & II (Weeks 11-12)
- • Generative AI and Computational Imaging I & II (Weeks 13-14)
- • Final Projects Q&A and Presentations (Weeks 15-16)
* Schedule subject to change. Updated schedule and presentation schedule available on course website.
Additional Information
Prerequisites
Students are expected to have background knowledge in:
- Linear algebra: vectors, matrices, tensors, dimensional analysis
- Signal processing: convolutions, Fourier transforms, linear systems
- Basic optics: lenses, light as rays and waves, cameras, image formation
- Programming: Python (preferred), PyTorch/TensorFlow, MATLAB
Before taking the class, you should be comfortable with basic camera image formation and able to read a recent ML conference paper and understand it at a conceptual level.
University Policies
Accessibility Resources
UNC facilitates reasonable accommodations for students with disabilities. Contact the Office of Accessibility Resources and Service (ARS) at ars.unc.edu or email ars@unc.edu.
Mental Health Resources
CAPS is committed to addressing mental health needs. Visit caps.unc.edu or visit their facilities on the third floor of Campus Health Services for walk-in evaluation.
Title IX and Safety
Students impacted by discrimination, harassment, or violence should contact the Director of Title IX Compliance (Adrienne Allison - Adrienne.allison@unc.edu) or Report and Response Coordinators (reportandresponse@unc.edu). Additional resources at safe.unc.edu.
Honor Code
All students are expected to follow the guidelines of the UNC honor code. It is particularly important that you cite the source of different ideas, facts, or methods and do not claim someone else’s work as your own. If you are unsure about which actions violate the honor code, feel free to ask the instructor.