Stefan Siemer

Stefan Siemer

Auto-generated profile, based on publicly available information

Stefan Siemer

University of Göttingen

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
22 October 2021
Verified
Book Chapter
Closed access
PDF file
MKMaria Kosche
Maria Kosche
TKTore Koß
Tore Koß
FMFlorin Manea
Florin Manea
SSStefan Siemer
Stefan Siemer

5 October 2023
Verified
Book Chapter
Closed access
PDF file
PFPamela Fleischmann
Pamela Fleischmann
SKSungmin Kim
Sungmin Kim
TKTore Koß
Tore Koß
FMFlorin Manea
Florin Manea
DNDirk Nowotka
Dirk Nowotka
MWMax Wiedenhöft
Max Wiedenhöft

1 August 2024
Verified
Conference Paper
Open access
PDF file
ZLZhengyang Lu
Zhengyang Lu
SSStefan Siemer
Stefan Siemer
PJPiyush Jha
Piyush Jha
JDJoel Day
Joel Day
FMFlorin Manea
Florin Manea
VGVijay Ganesh
Vijay Ganesh
Audio-driven talking face synthesis (TFS) enables the creation of realistic speaking videos by combining a single facial image with a speech audio clip. Unlike other facial features that naturally deform during speech, teeth represent unique rigid structures whose shape and size should remain constant throughout the video sequence. However, current methods often produce temporal inconsistencies and artifacts in the teeth region, resulting in a less realistic appearance of the generated videos. To address this, we propose OrthoNet, a plug-and-play framework designed to eliminate unrealistic teeth effects in audio-driven TFS. Our method introduces a Detail-oriented Teeth Aligner module, designed to preserve teeth details and adapt to their shape. It works with a Memory-guided Teeth Stabilizer that integrates a long-term memory bank for global teeth structure and a short-term memory module for local temporal dynamics. Through this framework, OrthoNet acts like an orthodontist for existing Audio2Video methods, ensuring that teeth maintain natural rigidity and temporal consistency even under varying degrees of teeth occlusion. Extensive experiments demonstrate that our method makes the teeth in generated videos appear more natural during speech, significantly enhancing the temporal consistency and structural stability of audio-driven video generation.

16 June 2025 in Journal of Computer and System Sciences
Verified
Journal Article
Open access
JDJoel D. Day
Joel D. Day
PFPamela Fleischmann
Pamela Fleischmann
MKMaria Kosche
Maria Kosche
TKTore Koß
Tore Koß
FMFlorin Manea
Florin Manea
SSStefan Siemer
Stefan Siemer

6 June 2025 in Theory of Computing Systems
Verified
Journal Article
Open access
PDF file
DADuncan Adamson
Duncan Adamson
PSPaul Sarnighausen-Cahn
Paul Sarnighausen-Cahn
MDMarius Dumitran
Marius Dumitran
MKMaria Kosche
Maria Kosche
TKTore Koß
Tore Koß
SSStefan Siemer
Stefan Siemer
We consider the longest common subsequence problem in the context of subsequences with gap constraints. In particular, following Day et al. (2022), we consider the setting when the distance (i. e., the gap) between two consecutive symbols of the subsequence has to be between a lower and an upper bound (which may depend on the position of those symbols in the subsequence or on the symbols bordering the gap) as well as the case where the entire subsequence is found in a bounded range (defined by a single upper bound), considered by Kosche et al. (2022). In all these cases, we present efficient algorithms for determining the length of the longest common constrained subsequence between two given strings, and discuss lower bounds for the respective problems.

1 November 2022
Verified
Book Chapter
Closed access
PDF file
PGPaweł Gawrychowski
Paweł Gawrychowski
FMFlorin Manea
Florin Manea
SSStefan Siemer
Stefan Siemer