COMP 776: Computer Vision in 3D World

Fall 2026

Instructor: Xiaoming Liu
Tuesday & Thursday, 9:30-10:45am, FB 007

[ Overview | Course Details | Schedule | Pre-Requisite ]

Course Description

This is an advanced graduate course focusing on fundamentals and recent development in 3D Computer Vision. The course will teach basic first principles of 3D Computer Vision and then discuss how modern deep learning techniques and first principles can work together to produce various state-of-the-art 3D reconstruction and generation techniques. The course will be lecture based. However the students will be assigned papers for reading and they are expected to lead the discussion and answer detailed questions about the papers. This course will also involve projects centered around 3D Computer Vision.

This course engages in diverse schoalrly perspectives to develop analytical and critical thinking and inclusion of any research paper does not imply endorsement



Office Hours Appointment via email.

Target Audience

MS & PhD students who have basic knowledges in Deep Learning and Computer Vision, and interested in diving deep into the fascinate world of 3D Computer Vision.

Goal/Student Learning Outcomes

(a) Develop fundamental mathematical models of 3D Computer Vision (b) Understand how modern deep learning techniques combined with fundamental 3D vision concepts produce SOTA results (c) Develop hands-on coding skill in 3D Computer Vision through course projects (d) Learn how to read papers and discuss them (e) Improve skills in presentation and leading discussions.

Grading

  • Course Project: 60% grade
  • 1 Paper Presentation: 10% grade
  • Class Participation: 10% grade
  • Mid-term in-class exam: 20% grade

Final Grades will be curved

Course Projects (60 points)

Format: Course Projects have 2 tracks, you need to choose 1: (I) Research and development of novel 3D algorithms or applications (II) Implementation and analysis of existing 3D computer vision algorithms.

Track I Research

Goal is to write a research paper that can be submitted to ICML, Neurips, CVPR or other conferences. The topic of the paper should involve 3D Computer Vision.

Team: The course encourage students from slightly different research backgrounds to form a team and explore new exciting research projects. Maximum group size is 2. Group size of 1 can be permitted under special circumstances.

Deliverables: 5 mins project pitch, 15 mins mid-term presentation, 15 mins final presentation. You will need to write minimum 4 page paper in CVPR format.

Grading: Grading will be based on quality of research, presentation, and actual progress throughout the semester. Project Pitch: 5pts; Midterm: 20pts -> 10pts presentation + Q&A, 10pts actual progress; Final: 35pts -> 10pts presentation + Q&A, 5pts actual progress, 20 pts for paper quality (e.g. 16-20- CVPR submittable, 10-16 - CVPR workshop submittable, 0-10 - below workshop quality). You will need to clarify whether the proposed project is a part of the research project you are working with your advisor or not. Expectations and grades will be scaled accordingly.

For help regarding Track I Research, contact instructor via email.

Track II Implementation and Analysis

You will be provided a list of 8 topics and you will be asked to choose 2 of these topics. For each topic you need to find 3 SOTA algorithms with publicly available code and a standard benchmark for evaluating the problem. After evaluating these 3 SOTA algorithms on standard benchmarks you need to capture your own images and analyze when these algorithms work well and when they fail.

Team: Only individual projects are allowed.

Deliverables: 5 mins project pitch highlighting which topics you will work on what algorithms+datasets you plan to use. Mid-term presentation will be on 1 topic and Final presentation is on the other topic. You need to prepare a technical report analysis your findings in CVPR format and submit your codebase for both projects independently.

Grading: Grading will be based on quality of analysis, presentation, and actual progress throughout the semester. Project Pitch: 5pts; Project I: 20pts -> 10pts presentation + Q&A, 10pts actual progress; Project II: 20pts -> 10pts presentation + Q&A, 10pts actual progress; 15pts for both tech reports.

Please read the guidelines for Track II PDF

For help regarding Track II Implementation and Analysis, contact the instructor.

Paper Reading & Presentation (10 points)

The students will be sent an online form within 1-2 week of the start of the class to indicate topics of interests. Paper reading assignments will be made by the instructor. Students will have 1 week to appeal the change of date or paper presentation topic. After this deadline, requests for change in paper reading will not be accomodated.

Each student will be assigned only 1 paper. The instructor will provide the overview of the research topic. The student need to present detailed technical analysis of the paper for 15-20 minutes, lead the discussion, and answer questions from students and instructor. This presentation will be more discussion focused.

Class Participation (10 points)

5 points for attendance: Attendance will be recorded. 5 points for attendance >=25 (out of 28 classes). 0.2 points will be deducted for every class missed thereafter. No exceptions.

5 points for participation in class discussion: Since this is a small discussion focused class, students are encouraged and expected to participate in class discussions by asking questions to instructor or paper presentor and sharing your own insights about the topic.

In-class Mid-term Exam (20 points)

Prepare for a 75 mins in-class midterm exam. Exam will have 50% basic math questions centered around 3D vision principles and 50% conceptual questions around advanced 3D techniques. Students are allowed to bring 1 page A4 sized cheat sheet for the exam. No electronics (phone, calculator, etc.) allowed for the exam.

Misc.

Late Submission & Accomodation Policies: No rescheduling of midterm or final presentation possible. The class is structured around a tight paper presentation schedule. Therefore, late assignments will not be accepted. If you have other deadlines you can always reschedule your paper presentation ahead of time.

Academic Integrity: For your presentations and projects, you are allowed to use materials from external sources. However, you must clearly acknowledge those sources.

Acknowledgement: Many of the course materials are credited to faculty and researchers in the community, including Prof. Roni Sengupta of UNC, Prof. Justin Johnson of UMich, etc. We appreciate their contributions.

Schedule