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

Technical University of Munich



Practical Course: Shape Reconstruction and Matching in Computer Vision (10 ECTS)

Summer Semester 2023, TU Munich



  • 16.03.2023: TUM matching will run a 2nd round between 21.03.23-23.03.23 .
  • 01.03.2023: Few positions are still available. You can send us your application mail (details see pre-meeting slides) before 11.03.2023 23:30.
  • 13.02.2023: Application deadline changed to 20.02.2023 23:30, please make sure sending your application mail before it, as well as applying in the tum matching system.
  • 02.02.2023: The course will be in hybrid format, you can participate no matter whether you are physically in Garching or not.
  • 01.02.2023: Preliminary meeting will take place at 14:00-15:00, 08.Feb.2023, in room 00.08.059 (5608.EG.059). You can also join via zoom. Preliminary meeting slides are available here.


Geometric shapes are ubiquitous in everyday life, ranging form rigid objects (tables, chairs, handicrafts) to deformable creatures (human, animals). The ability to reconstruct, generate and analyse geometric shapes is gaining importance and receiving increasing interest, both in academia and industry. In this practical course, we will study and solve challenging real-world problems in the area of 3D/4D shape reconstruction and analysis. Topics will include shape matching and correspondences, registration, recent metric spaces, reconstruction and generation. We will explore both classical geometry-bases methods and learning-based approaches.

Course Structure

The course will start with lectures and assignments to get familiar with the different topics. After that, you will work on a research oriented project in team (max. 2 persons). To review the progress and resolve open issue, you will meet the supervisors on a regular basis (max. bi-weekly). At the end of the practical course, you will be familiar with the basis concepts and tools in geometrical shape reconstruction and analysis, and gain hands-on experience through a research project, which may be extended to a publication.


  • Proficiency in python (or matlab)
  • Familiar with version control (git)
  • Comfortable with DL frameworks (pytorch, pyg etc.)
  • Good knowledge of basic mathematics, linear algebra, probability, numerics, analysis etc.
  • Participation in at least one of the offered deep learning labs, eg. I2DL,ADL4CV,IN2349
  • Or participation in at least one of the Multi-View Geometry labs, eg. MVG,VISNAV, IN2293


1. TUM Matching system:

  • All information on the matching system and process can be found here.

2. AND send your application via mail.

  • An application template is provided in the preliminary meeting slides.

Rechte Seite

Informatik IX
Computer Vision Group

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

Follow us on:



CVPR 2023

We have six papers accepted to CVPR 2023.


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.