This is an old revision of the document!
Seminar: Shape Analysis
Please register over the TUM matching system.
Seminar for computer science master students (IN2107) and mathematics bachelor and master students.
First Meeting (Introduction)
Location: Room 02.09.023
Time and Date: Friday, 26th January, 14:00
Weekly Meetings (Presentation)
Location: Room 02.09.023
Time and Date: Tuesday, 13:00 - 15:00
Start: Tuesday, 24th April
Presentations should be held in English.
Contact: shapeseminar@vision.in.tum.de
Description
Even though 3D objects have been used for decades in computer science, methods for the automatic analysis, recognition, categorization and comparison of these objects have become an active field of research only recently. These kind of techniques form the core of shape analysis and the object of this seminar.
In this seminar, we will review classical approaches to represent and analyze shapes and then study methods for automatic retrieval, matching, and processing of 3D models. The course will touch upon the most recent advances in the field. Particular emphasis will be put on defining similarity between shapes, descriptors that simplify their analysis, and developing efficient algorithms to match shapes and analyze their deformations. We will also discuss new research directions for shape analysis in real-world scenarios, such as those arising in practical applications where the 3D data is captured with depth sensors and the shapes suffer from noise and artifacts.
Organizers
Final Report
Final reports should be written in LaTeX using the provided template: Report template.
Timetable
Each week there will be two presentations. More details are listed here.