Sebastian Koch

Hi! I am a PhD student at Ulm University and Bosch Research/Bosch Center for Artificial Intelligence. I am supervised by Timo Ropinski.

My main research interest lies at the intersection of computer vision and robotics. The goal of my PhD is to develop 3D scene representations of the real world that are valuable for robots to navigate and solve tasks within their environment.

I completed my master's degree in computer science at the University of Tübingen. In my master's thesis, I investigated multi-view and symmetry-aware 6D pose estimation under the guidance of Andreas Geiger and Gerhard Neumann, in collaboration with BCAI. Additionally, I worked as a research assistant in the Cognitive Systems lab, focusing on hardware-efficient remote sensing methods with Andreas Zell. Before that, I pursued my bachelor's degree in computer science at DHBW Stuttgart. I also gained practical experience through multiple internships at Bosch, with focus on perception in robotics and autonomous driving.

Email  |  CV  |  GitHub  |  Google Scholar  |  LinkedIn  |  Twitter

Sebastian Koch

Hi! I am a PhD student at Ulm University and Bosch Research/Bosch Center for Artificial Intelligence. I am supervised by Timo Ropinski.

My main research interest lies at the intersection of computer vision, and robotics. The goal of my PhD is to develop 3D scene representations of the real world that are valuable for robots to navigate and solve tasks within their environment.

I completed my master's degree in computer science at the University of Tübingen. In my master's thesis, I investigated multi-view and symmetry-aware 6D pose estimation under the guidance of Andreas Geiger and Gerhard Neumann, in collaboration with BCAI. Additionally, I worked as a research assistant in the Cognitive Systems lab, focusing on hardware-efficient remote sensing methods with Andreas Zell. Before that, I pursued my bachelor's degree in computer science at DHBW Stuttgart. I also gained practical experience through multiple internships at Bosch, with focus on perception in robotics and autonomous driving.

Email  |  CV  |  GitHub  |  Google Scholar  |  LinkedIn  |  Twitter

News
  • 04/2024 I was accepted at the prestigious International Computer Vision Summer School ICVSS 2024.
  • 02/2024 My paper Open3DSG got accepted at CVPR 2024! I will also present it at the OpenSUN & SG2RL workshop.
  • 10/2023 My paper SGRec3D got accepted at WACV 2024!
  • 10/2023 My paper Lang3DSG got accepted at 3DV 2024!
  • 08/2023 I got an workshop paper accepted at the SG2RL workshop held at ICCV 2023 in Paris!
  • 07/2023 Our follow-up paper to my master's thesis SyMFM6D has been accepted at RA-L
  • ---- show more ----
Research
Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and
Open-Set Relationships

Sebastian Koch, Narunas Vaskevicius, Mirco Colosi, Pedro Hermosilla, Timo Ropinski
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) , 2024
paper | project page | poster | code | video | bibtex

The first open-vocabulary 3D scene graph method with open-world relationships.

Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction
Sebastian Koch, Pedro Hermosilla, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski
International Conference on 3D Vision (3DV), 2024
paper | project page | poster | bibtex

Language and 3D scene graph alignment using contrastive pre-training.

SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction
Sebastian Koch, Pedro Hermosilla, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski
IEEE Winter Conference on Applications of Computer Vision (WACV), 2024
paper | project page | poster | video | bibtex

A label-efficient method to predict 3D semantic scene graphs for indoor environments.

SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation
Fabian Duffhauß, Sebastian Koch, Hanna Ziesche, Ngo Anh Vien, Gerhard Neumann
IEEE Robotics and Automation Letter (RA-L), 2023 & International Conference on Robotics and Automation (ICRA) 2024
paper | code | bibtex

A 6D pose estimation approach utilizing multiple viewpoints and considering object symmetries.

Multi-View RGB-D Fusion for 6D Pose Estimation
Sebastian Koch,
M.Sc. Thesis, University of Tübingen, 2022
thesis | slides | bibtex

Comprehensive Analysis of the Object Detection Pipeline on UAVs
Leon Amadeus Varga, Sebastian Koch, Andreas Zell,
Remote Sensing, 2022
paper | code | bibtex

---- More ----

template adapted from this awesome website