Practical Course: Shape Reconstruction and Matching in Computer Vision (10 ECTS)
Summer Semester 2023, TU Munich
Organization
- Contact: srmcv-ss23@vision.in.tum.de (please address all requests to this address only!)
News
- 26.04.2023: Update the Wednesday session to 14:15-15:45 (sharp) due to course conflicts.
- 03.04.2023: All accepted students will be registered to the lab course by us. Stay tuned for the 1st video lecture.
- 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.
General
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.
Prerequisites
- 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.
Application
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.
Account