Patricia Gschoßmann

I'm a PhD student at the University of Tübingen in the Autonomous Vision Group, led by Prof. Dr.-Ing. Andreas Geiger. My research is supported by the International Max Planck Research School of Intelligent Systems .

My research interests lie at the intersection of computer vision (3D vision), machine learning (deep learning), and computer graphics (geometry, rendering). My current research focuses on advancing 3D scene representations, with a particular emphasis on high-fidelity surface reconstruction and efficient mesh extraction.

Before starting my PhD, I worked as a computer vision and deep learning intern for augmented reality at BMW on the AR glasses research project, which was showcased at CES 2024 . Prior to that, I completed my M.Sc. in Computer Science at the Technical University of Munich, after receiving my B.Sc. in Computer Science from Ludwig Maximilian University of Munich.

Feel free to reach out - I'm always happy to connect!

CV Mail GitHub Bluesky X

Publications

ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives
Bartłomiej Baranowski, Stefano Esposito, Patricia Gschoßmann, Anpei Chen, Andreas Geiger
2026 International Conference on 3D Vision (3DV), 2026
Paper / Code /

@InProceedings{Baranowski20263DV, 
	author = {Bartłomiej Baranowski and Stefano Esposito and Patricia Gschoßmann and Anpei Chen and Andreas Geiger}, 
	title = {ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives}, 
	booktitle = {2026 International Conference on 3D Vision (3DV)}, 
	year = {2026}, 
}

Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
Soubarna Banik, Patricia Gschoßmann, Alejandro Garcia, Alois Knoll
2023 International Joint Conference on Neural Networks (IJCNN), 2023
Paper / Code /

@InProceedings{Banik2023IJCNN, 
	author = {Soubarna Banik and Patricia Gschoßmann and Alejandro Garcia and Alois Knoll}, 
	title = {Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation}, 
	booktitle = {2023 International Joint Conference on Neural Networks (IJCNN)}, 
	year = {2023}, 
}

Website template provided by Michael Niemeyer. Check out his GitHub repository for instructions on how to use it.