Gregor Kobsik
DEEP LEARNING ENTHUSIAST and PASSIONATE BALLROOM DANCER
Greetings! As a PhD student specializing in 3D deep learning, I have had the privilege of researching and developing transformer-based models for object generation and delving into local symmetry detection through contrastive learning techniques. For further insights into my previous projects and research, please feel free to visit my RESEARCH & PROJECTS page. Apart from my academic pursuits, I am passionate about ballroom dancing, photography, board games, and enjoy traveling and engaging in DIY projects.
Featured project:
"Development of a Heuristic-based Agent for an Interactive Multiplayer Game", 2021, 1st place - informatiCup
Personal & Hobbys
Ballroom Dancing
Ballroom dancing is not just a hobby for me; it is a passion that drives me to train rigorously multiple times a week, actively engage in dance parties, and eagerly participate in regional competitions.
Photography
My journey began with capturing mesmerizing dance photos. However, it wasn't long before my camera became a constant companion on all my trips and adventures, nurturing my profound love for photography.
Board Games
I find great enjoyment in engaging with my friends through the world of card and board games. From casual favorites to intricately designed ones with complex mechanics, I embrace the challenge and thrill that these games bring.
Traveling & Nature
When I am not occupied with my work at the desk or lost in the enchanting world of dance, I take pleasure in exploring the beauty of nature through hiking or riding my mountain bike.
Research & Projects
Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences
M. Ibing, G. Kobsik, L. Kobbelt, 2023, Conference on Computer Vision and Pattern Recognition (CVPR) - StruCo3D Workshop
Based on the findings of my master thesis, we formulated a fully autoregressive decoding scheme for the transformer architecture using octrees to generate 3D shapes. Despite not archieving a novel SOTA, we showed that the approach is a viable alternative to current generative models and able to generate a wide variety of diverse shapes, both conditionally and unconditionally.
Shape Generation utilizing Octrees with Self-Attention Networks
G. Kobsik, 2021, Master Thesis, RWTH Aachen University
I researched different formulations of autoregressive self-attention encoder and decoder neural networks with the goal of generating 3D shapes. Especially, I formulated the shape generation task as a sequence generation task on a linearized octree structure and thus was able to apply SOTA natural language processing models to the field of shape generation, e.g. the transformer architecture. A remarkable property of the formulation is the ability to inherently define voxel super-resolution as a sequence completion task.
Development of a Heuristic-based Agent for an Interactive Multiplayer Game
G. Kobsik, R. Kupper, M. Pozor, 2021, Competition Submission, informatiCup 2021
This project is the contribution to the informatiCup challange 2021 of the German Informatics Associaty (GI). We developed our own heuristic-based AI agent that is able to competitively play the game of spe_ed. Our submission was selected among many others for the final round of the contest, in which we placed 1st.
Aided Hand Detection in Thermal Imaging using RGB Stereo Vision
M. Schmieschek, G. Kobsik, A. Stollenwerk, S. Kowalewski, T. Orlikowsky, M. Schoberer, 2019, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
During my bachelor studies, I was able to support the development of a contact-free hand desinfection validation application based on a thermal camera combined with two RGB cameras. Our goal was to develop a system, which is able to detect and segment a hand as robustly as possible to detect temperature gradients before and after the desinfection of hands and thus support the medical personal in their daily desinfection routine to prevent the spread of infections in clinical environments.
Foam Generation for Particle-based Fluid Simulations
G. Kobsik, 2018, Bachelor Thesis, RWTH Aachen University
My first scientific research focused on the generation and advection of foam particles in fluid environments to enhance the visual appearance of the simulations. Based on observations and a simple approximation of the underlying physical behaviour, I was able to depict different interactions of air with water to add physically-based effects like foam, bubbles or spray in dynamic scenes.