Direkt zum Inhalt springen
Computer Vision Group
TUM School of Computation, Information and Technology
Technical University of Munich

Technical University of Munich



Practical Course: Correspondence and Matching Problems in Computer Vision (10 ECTS)

Winter Semester 2020/2021, TU München

Organisers: Prof. Dr. Florian Bernard, Maolin Gao, Tarun Yenamandra

Please direct questions to cmpcv-ws20@vision.in.tum.de


2020-09-11: [gitlab account] collect your gitlab using the table at the bottom of the page.

2020-08-18: [topic assignment] see the topic assignment and grouping here.

2020-08-14: [application closed] accepted applicants have been informed via mail.

2020-07-30: [application update] We have some vacancies open for applications. Please send your application (details see below) to cmpcv-ws20[at]vision.in.tum.de until 09 August 2020 23:59 CEST. Application results will be given till 14 August 2020 if successful.

2020-07-16: [application] Please send applications (indicating learning goals; grade transcripts; programming skills; background in mathematics, optimisation and visual computing) to cmpcv-ws20[at]vision.in.tum.de . Sending an email with sufficient info about yourself until 23 July is crucial for matching success.

2020-07-15: [preliminary meeting] Slides from the preliminary meeting are available here (you need to log-in with the same account that you use in TUMonline).

Course Description

Correspondence and matching problems are omnipresent in computer vision and related fields. Such problems can appear in many different contexts (e.g. image alignment, shape matching, object tracking, 3D reconstruction, etc.), which highlights their high relevance. Most commonly, such problems are phrased in terms of numerical optimisation problems, as machine learning prediction tasks, or as a combination of both. During this course students will work on a specific project that tackles a particular correspondence or matching problem setting. They will implement and analyse methods described in existing research papers, as well as understand and analyse their strengths and weaknesses. The topics will be related to:

  • Graph matching
  • Image alignment
  • Point-cloud registration
  • Shape matching
  • Deep learning
  • Feature learning
  • Multi-matching problems
  • Cycle-consistency of maps

It is expected that all participants have excellent programming skills in a scientific programming language (e.g. Matlab or Python), a thorough understanding of algorithms and data structures, as well as a solid working knowledge of linear algebra and calculus.

In addition, students should have a background in at least one of the following topics: continuous/discrete optimisation, 3D geometry, computer vision, image processing, or computer graphics.

Moreover, important soft skills include communication skills, the ability to identify what is unclear, to figure out what questions need to be asked to clarify it, to formulate the questions clearly, and to ask the tutor without hesitation. Communicating well and strategically is an important rule of the practical course. Almost all difficulties experienced by students are due to not following these rules.

Course Structure

At the beginning of the course, relevant basics of correspondence and matching problems, including theoretical and practical aspects, will be covered in lectures. Subsequently, students will work on practical projects in groups of 2-3. In order to ensure an appropriate progress of the students, there will be regular communication with tutors. At the end of the project, each group will present their project with a following Q&A session. There will be no additional written or oral exam. Both the theoretical and practical part of the project will be considered in the final grading.

Course Schedule

See here.

GitLab Account

Rechte Seite

Informatik IX
Computer Vision Group

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:



NeurIPS 2022

We have two papers accepted to NeurIPS 2022.


WACV 2023

We have two papers accepted at WACV 2023.


Fulbright PULSE podcast on Prof. Cremers went online on Apple Podcasts and Spotify.


MCML Kick-Off

On July 27th, we are organizing the Kick-Off of the Munich Center for Machine Learning in the Bavarian Academy of Sciences.


AI Symposium

On July 22nd 2022, we are organizing a Symposium on AI within the Technology Forum of the Bavarian Academy of Sciences.