I am a second-year PhD student supervised by Prof. Andreas Geiger and I am also part of the machine learning team of the ETAS GmbH, Bosch Group.
In recent years, deep generative models have shown great performance on several tasks in the 2D domain. In my PhD, I am working on generative models in the 3D domain. My aims are to generate full 3D objects and to reconstruct 3D objects given some input condition like an image of the object.
2014 - 2017 Master of Science in Physics, University of Stuttgart
Emphasis: Nonlinear and Stochastic Dynamics, Thermodynamics
Thesis: “Thermodynamic consistent Approximations of Stochastic Processes with nonadditive Noise”
2011 - 2014 Bachelor of Science in Physics, University of Stuttgart
Thesis: “Colloidal Suspension as a Thermostat of an Hamiltonian System”
2016 Student assistant, II. Institute for Theoretical Physics in Stuttgart
WS 14/15 and SS 15 Teaching assistant, Lab courses
WS 13/14 Teaching assistant, Lecture Experimental Physics I
In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, 2019 (inproceedings)
With the advent of deep neural networks, learning-based approaches for 3D~reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learning-based 3D~reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose occupancy networks, a new representation for learning-based 3D~reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems