Advanced Topics in 3D Computer Vision

Overview

This course focuses on different recent topics in 3D computer vision and their application.
The first set of lectures on specific vision problems (such as 6D Pose Estimation, Structure from Motion, Depth Estimation, Reconstruction) lays the foundation for practical challenges carried out by the student individually.

While working on these problems the student gets familiar with these topics and decides on a direction for the group phase.
In the group phase, a group of students is supported by coaches from both industry and academia. The group identifies a particular 3D vision problem in one of these areas and develops a prototype to solve it. The prototype solution is finally presented with a live demonstration.

After the course, the student is familiar with some advanced topics in 3D computer vision for which a practical implementation has been carried out and experience in problem-solving for a specific 3D vision problem has been learned in constant exchange with group members and vision experts.

For any questions, please contact: at3dcv@mailnavab.informatik.tu-muenchen.de

Announcements

  • Application Deadline: 15.02.2023
  • Preliminary Meeting: February, 07.02.2023 at 11am via zoom

Registration

For the application, please use the following form (Application Deadline: 15.02.2023): tba

Please also register in the TUM matching system for the course. Keep in mind that your chances to be assigned to the course increase if you give it a higher rank in your choices. For further details about how the matching system works and its schedule please check this website.
We select appropriate candidates based on their background, interests, and motivation.

Material

Master-Praktikum - Advanced Topics in 3D Computer Vision (IN2106, IN4023)

TypePractical course
Duration6 SWS
TermSommersemester 2024
Language of instructionEnglish
Position within curriculaSee TUMonline

Dates

Prerequisites

Students should have basic knowledge in Python programming as well as in computer vision concepts. Ideally, experience with OpenCV and Pytorch (or a similar library) exists and methods such as camera calibration and nonlinear optimization are known.

Teaching and learning methods

- Lectures on specific 3D computer vision topics - Individual assignements - Group project and presentation

Examination

Immanent evaluation based on individual assignments, course participation, group project

Links