ETH Zurich - D-INFK - IVC - CVG - Lectures - 3D Vision

3D Vision


This course was called 3D Photography at the time of teaching.

Instructors: Prof. Marc Pollefeys, Dr. Kalin Kolev
Teaching assistants: Yagiz Aksoy, Bernhard Zeisl, Office hours: Mo. 11:30 - 12:30, Fri. 11:15 - 12:15
Lectures: Mondays from 09:00-12:00 in CAB G51
Prerequisite: Computer Vision lecture from last semester, particularly the camera model, geometric aspects and structure-from-motion. If you have not attended that class, there will be a very short repetition, but you will have to study necessary basics yourself in order to work on your project and understand papers.

Course Descriptions

This course aims to provide students with knowledge on several topics in 3D photography. In each class, an introductory lecture on a selected topic will be given first. Then students will give presentations of selected papers relevant to the topic of the week. A maximum of 2 papers shall be presented in each lecture.
Other students are encouraged to engage in the paper presentations through active discussions. To organize the discussion in a more lively way, each student will be assigned to lead the discussion of an other student's presentation; i.e. this student acts as an "opponent" or moderator and actively supports the discussion by asking relevant questions wrt. the the presented paper and motivates other students to contribute.

Over the semester students will work on a project related to a topic in 3D photography in collaboration with a team member of our computer vision group (CVG). We will provide project ideas for this purpose. The project can be done individually or in a team of 2 people. Students will give a final presentation/demo of their projects at the end of the semester.

Grading Scheme

  1. 25%: Paper presentation (incl. discussion moderation)
  2. 75%: Final project which includes a report and presentation/demo

Course Schedule

Please refer to the subpage for the course content and lecture slides.

Student Projects

Each student (group) is required to hand in and present a project proposal within the first three weeks of the semester. Each team will present their project proposal in a 5 min presentation to the whole class.

For this purpose we create a list of project suggestions, but you are free to propose your own project. Make sure to talk to the supervisor and discuss the project with him/her!!

The proposal should be 1-2 pages describing what you want to do in the project, and how you plan to achieve your envisioned results. A good ideas is to identify the algorithmic and technological challenges within the project. Try to address each of them individually and explain your considered solutions; also make an attempt to think about alternatives if you believe a particular approach is unstable or likely to fail.

Midterm presentations have the purpose that you present what you did so far and that you get feedback. So you are encouraged to raise open questions. This is a possibility for us to stear the project and help you, if you got stuck.

Final presentations will be held like a poster presentation at a conference. Thus you are expected to prepare a poser about your project and explain your work to the class. Slides as in a standard presentation do not need to be prepared.
In addition, you are required to hand in a technical report for your project. The report format should be in parallel with 3DV paper format. Latex and Word templates can be found here.

In a nutshell this is the schedule for your projects:

Project assignment deadline: Fr. February 28th. 2014, 23:59 (by this date you need to form the groups and let us know about your team members and your project topic)
Proposal submission deadline: Fr. March 7th. 2014, 23:59 (submit as PDF via email to Kalin, Yagiz and Bernhard)
Proposal presentation: Mo. March 10th. 2014 (5min for each team)
Midterm presentation: Mo. April 14th. 2014 (10 min for each team; your are expected to given an update and also to raise open questions and get feedback)
Final project demonstrations: Mo. May 26th. 2014 (10min for each team followed by question & answer session)
Final project technical report: Mo. June 2nd. 2014, 23:59 (6-8 pages, 3DV style paper template)

Student Paper Presentations

Each project group needs to present a paper related to the lecture content.
Please see the list of papers to present by students for more details.

Discussion Forum

There exists a discussion forum page in ILIAS for this course.
Students should sign in using their ETHZ accounts and participate in the discussion forums. Please put all your discussions related to the lectures, paper presentations and projects there.

Available hardware for projects

Students are encouraged to use their own SLR/digital cameras, phones, open source datasets (e.g. examples from flickr), etc. for their projects. However, students who do not own any of the equipment could also make arrangements with our lab for any of the listed equipment.

Following hardware is available: Students with project idea that require any other special equipment please talk to us!

Some useful links

Open Source Computer Vision (OpenCV) - lots of computer vision algorithms
Point Cloud Library (PCL) - provides interface to Kinect sensor and 3D modeling algorithms
Camera calibration toolbox for Matlab


© CVG, ETH Zürich lm@inf.ethz.ch