Winter Semester 2024/2025, TU München

Organisers: Viktoria Ehm, Maolin Gao, Dr. Riccardo Marin

2024-07-04: The preliminary meeting will take place at 11:00 - 12:00 on 05.07.2024 in seminar room 02.09.014. The slides will be published afterwards. You are encouraged to participate and ask questions directly in the meeting, since it will positively affect the matching process. Please find the zoom link in TUMonline.

October 21st, 2024: The paper list will be published.

November 4th, 2024: Submit your top 4 preferences from the paper list.

November 4th, 2024: Last chance to withdraw from the seminar. After this date, any withdrawal will result in a final grade of 5.0. We will register you in TUMonline at this time.

November 18th, 2024: Papers will be assigned to each student based on preferences.

November 18th, 2024 - January 7th, 2025: Reading and exploration period with your supervisor.

January 8th-9th, 2025: Block seminar.

3D Shape Matching problems are ubiquitous in computer vision, graphics and related fields. Such problems can appear in many different contexts, e.g. shape correspondences, object tracking, 3D reconstruction and interpolation etc., which highlights their high relevance. In this seminar, we will review the classic and recent advances in 3D shape matching, both optimisation-based and machine-learning-based approaches. Students will read a list of selected research papers, and each student will deeply study the problem setting and methods described in one existing paper under our supervision, and report the final outcome in terms of open presentations followed with a Q&A session and reports. There will be no additional written or oral exam.

After attending the seminar, we expect the participants should have a good overview of current approaches to tackle 3D shape matching problems, and a deeper understanding about one particular method, which should lay a good foundation of future hands-on research projects.

All participants should have a solid working knowledge of linear algebra and calculus. In addition, it is useful (but not required), that students have a background in at least one of the following topics: continuous/discrete optimisation, 3D geometry, computer vision, image processing, or computer graphics.

Slides can be found here .