Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich



IN2107 - Seminar (Image Segmentation and Shape Analysis)

Please register over the TUM matching system.

Seminar for computer science master students (IN2107).

First Meeting (Introduction)

Location: Room 02.09.023
Time and Date: Wednesday, 29th June, 13ct - 14

Weekly Meetings (Presentation)

Location: Room 02.09.023
Time and Date: Wednesday, 14ct - 16
Start: Wednesday, 26th October
Presentations have to be held in English.

Contact: shapeseminar@vision.in.tum.de


A classical computer vision problem is image segmentation. Here, we like to group those pixels that belong to the same semantic object. In recent years, these problems are considered for 3D image data.

Independent of these segmentation problems, 3D data has been used for decades in computer science. Nevertheless, methods for the automatic analysis, recognition, categorization and comparison of 3D shapes have become an active field of research only recently.

In this seminar, we will discuss how these two apparently different research topics interact and provide us with a better understanding of the surrounding world.

The course will touch upon

  • Binary and Multi-Label Image Segmentation
  • Shape Analysis in 2D and 3D
  • Shape Prior for Image Segmentation

Point Descriptor Learning
Point Descriptor Learning

Shape Descriptors
Shape Descriptors


Final Report

Final reports should be written in LaTeX using the provided template: Report template.


Each week there will be two presentations. More details are listed here.

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

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

Follow us on:
CVG Group DVL Group



Richard Szeliski (University of Washington) will give a talk in the TUM AI lecture series on Jan 28th, 5pm! Livestream


Frank Dellaert (Georgia Tech) will give a talk in the TUM AI lecture series on Dec 17th, 4pm! Livestream


Jon Barron (Google) will give a talk in the TUM AI lecture series on Oct 22nd, 9pm! Livestream


We have five papers accepted to 3DV 2020!


Our effcient deep network architectures form the AI engine of the project Slow Down COVID-19 at Harvard.