Johann Marius Zöllner

Johann Marius Zöllner

Auto-generated profile, based on publicly available information

Johann Marius Zöllner

Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology (KIT) 76131 Karlsruhe Germany

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

23 January 2019
Verified
Book Chapter
Closed access
PDF file
FPFlorian Piewak
Florian Piewak
PPPeter Pinggera
Peter Pinggera
MSManuel Schäfer
Manuel Schäfer
DPDavid Peter
David Peter
BSBeate Schwarz
Beate Schwarz
MZMarius Zöllner
Marius Zöllner


12 July 2025 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
MMMartin Mayr
Martin Mayr
MDMarcel Dreier
Marcel Dreier
FKFlorian Kordon
Florian Kordon
MSMathias Seuret
Mathias Seuret
JZJochen Zöllner
Jochen Zöllner
VCVincent Christlein
Vincent Christlein
The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. We set a new benchmark in our comprehensive evaluation, achieving 61 % mAP and 56 % top-1 accuracy in style preservation, significantly outperforming the previous best method (37 % mAP, 30 % top-1). We are making our code publicly available for reproducibility, supporting research in this area and research into potential countermeasures: https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm

22 September 2022 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
LTLarissa T. Triess
Larissa T. Triess
CRChristoph B. Rist
Christoph B. Rist
DPDavid Peter
David Peter
JZJ. Marius Zöllner
J. Marius Zöllner
A considerable amount of research is concerned with the generation of realistic sensor data. LiDAR point clouds are generated by complex simulations or learned generative models. The generated data is usually exploited to enable or improve downstream perception algorithms. Two major questions arise from these procedures: First, how to evaluate the realism of the generated data? Second, does more realistic data also lead to better perception performance? This paper addresses both questions and presents a novel metric to quantify the realism of LiDAR point clouds. Relevant features are learned from real-world and synthetic point clouds by training on a proxy classification task. In a series of experiments, we demonstrate the application of our metric to determine the realism of generated LiDAR data and compare the realism estimation of our metric to the performance of a segmentation model. We confirm that our metric provides an indication for the downstream segmentation performance.

1 June 2007 in 2007 IEEE Intelligent Vehicles Symposium
Verified
Conference Paper
Closed access
SVStefan Vacek
Stefan Vacek
TGTobias Gindele
Tobias Gindele
JZJ. Marius Zollner
J. Marius Zollner
RDRudiger Dillmann
Rudiger Dillmann
Driving a car in urban areas autonomously requires the ability of an in-depth analysis of the current situation. For understanding the current situation and deducing consequences for the execution of behaviors (maneuvers), higher-level reasoning about the situation has to take place. In this paper, an approach for situation interpretation for cognitive automobiles is presented. The approach relies on case-based reasoning to predict the evolvement of the current situation and to select the appropriate behavior. Case-based reasoning allows to utilize prior experiences in the task of situation assessment.