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.
NeRSemble reconstructs high-fidelity dynamic-radiance fields of human heads. We combine a deformation for coarse movments with an ensemble of 3D multi-resolution hash encodings, which act as a form of expression dependent volumetric texture that models fine-grained, expression-depndent details. Additionally we propose a new 16 camera multi-view capture dataset (7.1 MP resolution and 73 frames per second) containing 4700 sequences of more than 220 human subjects.
Tobias Kirschstein, Shenhan Qian, Simon Giebenhain, Tim Walter, Matthias Nießner
NPHM is a field-based Neural parametric model for human heads, that represents identity geometry implicitly in a cononical space and models expressions as forward deformations. The SDF in canonical field is represented as an ensemble of local MLPs centered around facial anchor points. To train our model we capture a large dataset of complete head geometry containing over 250 people in 23 expressions each using high quality structured light scanners.
Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz, Lourdes Agapito, Matthias Nießner
In Neural Puppeteer (NePu) we explore single-evaluation-per-pixel neural rendering for dynamic objects. In particular we learn a latent space that relates the 3D pose of an object with multiple renderable properties, such as occupancy masks, color and depth. The fast rendering speed allows us to tackle 3D keypoint detection by inverse rendering from multi-view sillhouettes. Using silhouettes alone, we obtain an appearance and lightning invariant representation, that we can fit to real images, in a zero-shot-synthtetic-to-real scenario.
Simon Giebenhain*, Urs Waldmann*, Ole Johannsen, and Bastian Goldluecke
More information on our Project Page.
AIR-Net is the first encoder-based, grid-free, local and implicit 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 and 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 already outperforms 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