Seminar for computer science master students (IN2107).

Three­-dimensional data has been used for decades in computer science. Nevertheless, methods for the automatic analysis, recognition, categorization and comparison of 3D objects have become an active field of research only recently. In this seminar, we will start by reviewing the classical approaches in the literature and then proceed to investigate methods for automatic retrieval and analysis of 3D models. The course will touch upon the most recent advances in the field. Particular emphasis will be put on defining and computing similarity between shapes, when these shapes are allowed to undergo non­rigid deformations (e.g. different poses of a human model) and different optimization techniques to obtain good and efficient solutions.

• Organizer: Prof. Florian Bernard, Zorah Lähner, Marvin Eisenberger
• Email: shapeseminar@vision.in.tum.de

• Date: Wednesday, January 29th, 2020
• Time: 10:00 - 11:00
• Location: 02.09.023
• Attendance of the pre-meeting will give you priority in the matching system.
• Please contact us in advance if you are not able to attend the pre-meeting.

• Registration is done via the TUM matching platform for computer science students and via TUMonline for mathematics students.
• Registration deadline is ??.
• Attendance is mandatory and the weekly meeting time (see below) will not be changed, so please do not register if it clashes with another lecture you will attend.
• Further information about registration and criteria for selection of participants will be given in the pre-meeting.

• Day: Wednesday
• Time: 14:00 - 16:00
• Start: TBA
• Each week there will be two talks.
• All talks are held in English.

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

The list of topics and slides of the premeeting can be found here.