Open Student Projects

How To Apply

Please read this section carefully. I might not answer you if you do not follow the instructions and I am very busy at the moment (or just reply with a link here).

In order to apply write an email to laehner [at] uni-bonn.de with at least the following information:

a short introduction of yourself including your study program, semester and programming languages you have experience with
which of the projects below you want to do, or a short proposal of your own topic (make sure to point out how the topic is related to my research)
your transcript of records (this is the list of your courses and grades you can get from Unisono)

Optional but appreciated:

your CV
a description of experience you have with handling geometric data (for example the lecture “Advanced Topics in Computer Graphics II”)
any questions/constraints you have for your thesis

Available Projects

Currently available spots: 2

All projects related to deep learning need to be implemented in PyTorch.

Analysis of Autoencoder Latent Spaces

Summary: Survey, implement and compare existing autoencoder architectures for point clouds, voxel grids and triangle meshes.

Suitable for: Bachelor Thesis, Master Thesis

Requirements: Python, passed our Deep Learning lecture (exception for Bachelor students)

Analysis of Functional Maps framework using different basis sets

Summary: Survey, implement and compare the behavior of functional maps when replacing the default Laplace-Beltrami eigenbasis with different sets of basis functions.