I am a final year master’s student at the University of Konstanz.
My general areas of interest are machine learning and computer vision.
More specifically, I am highly interested in Geometric Deep Learning and Neural Scene Representations.
Currently I am working on my master’s thesis under the supervision of Prof. Bastian Goldlücke, where I am exploring how a geometrically inspired neural network design can benefit neural implicit shape representations for 3D reconstruction.
In my future research I hope to take steps towards algorithms, that like humans, easily perceive, understand and abstractly reason about their 3D environments from few observations.
AIR-Net is the first encoder-based, grid-free, implcit shape representation model. Our network design focuses on conformity with geometric properties like permutation invariance and translation equivariance of the point cloud. Furthermore, our network operates on the k-nearest-neighbor graph, which encodes an effective anf efficient inductive bias. Using an expressive decoder, we are able to condition an implicit function on a sparse set of local latent vectors. While this simple latent representation certainly offers exciting avenues for future work, our model is still significantly outperforming the previous state-of-the-art.
Simon Giebenhain and Bastian Goldlücke
Code available here.
The safety of autonmous vehicles is heavily dependent on the reliability of its underlying sensor measurements. While radar is often overlooked, its all-day, all-weather and long-range capabilities, as well as, low price render it a promising candidate. In this paper we introduce an attention based sensor-fusion method, to filter out false-positive detections (so called ghost targets) in radar.
LeiChen Wang, Simon Giebenhain, Carsten Anklam, Bastian Goldlücke