Recent publications

February 2024

Towards Better Morphed Face Images Without Ghosting Artifacts

Clemens Peter Seibold, Anna Hilsmann

We propose a method for automatic prevention of ghosting artifacts based on a pixel-wise alignment during morph generation. We evaluate our proposed method on state-of-the-art detectors and show that our morphs are harder to detect, particularly,...


February 2024

Generative Texture Super-Resolution via Differential Rendering

Milena Teresa Bagdasarian, Peter Eisert, Anna Hilsmann

We propose a generative deep learning network for texture map super-resolution using a differentiable renderer and calibrated reference images. Combining a super-resolution generative adversarial network (GAN) with differentiable rendering, we...


February 2024

Multi-View Inversion for 3D-aware Generative Adversarial Networks

Florian Tim Barthel, Peter Eisert, Anna Hilsmann

Our method builds on existing state-of-the-art 3D GAN inversion techniques to allow for consistent and simultaneous inversion of multiple views of the same subject. We employ a multi-latent extension to handle inconsistencies present in dynamic...


February 2024

Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances

Paul Knoll, Peter Eisert, Anna Hilsmann, Wieland Morgenstern

We introduce a novel NeRF-based framework for pose-dependent rendering of human performances where the radiance field is warped around an SMPL body mesh, thereby creating a new surface-aligned representation. Our representation can be animated...


February 2024

Efficient and Accurate Hyperspectral Image Demosaicing with Neural Network Architectures

Eric Wisotzky, Peter Eisert, Anna Hilsmann, Thomas Wittenberg, Lara Wallburg, Stefan Göb

This study investigates the effectiveness of neural network architectures in hyperspectral image demosaicing. We introduce a range of network models and modifications, and compare them with classical interpolation methods and existing reference...


February 2024

Insights into the inner workings of transformer models for protein function prediction

Markus Wenzel, Nils Strodthoff, Erik Grüner

We explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extending the widely used XAI method of integrated gradients such that latent...


February 2024

Semantic Communication for Edge Intelligence: Theoretical Foundations and Implications on Protocols

Zoran Utkovski, Slawomir Stanczak, Johannes Dommel, Giuseppe Caire, Andrea Munari, Pin-Hsun Lin, Max Franke, André C. Drummond

Recent attention to semantic communication, driven by task-oriented solutions, aims to optimize resource use. Despite perceived efficiency gains, few practical implementations exist. This paper revisits theoretical foundations, emphasizing...


January 2024

Towards an AI-enabled Connected Industry: AGV Communication and Sensor Measurement Datasets

Rodrigo Hernangómez, Slawomir Stanczak, Martin Kasparick, Gerhard Fettweis, Daniel Schäufele, Rafail Ismayilov, Oscar Dario Ramos-Cantor, Hugues Tchouankem, Philipp Geuer, Alexandros Palaois, Cara Watermann, Mohammad Parvini, Anton Krause, Thomas Neugebauer, Jose Leon Calvo, Bo Chen

We present iV2V and iV2i+, two machine-learning datasets for industrial wireless communication. The datasets cover sidelink and cellular communication involving autonomous robots together with localization and sensing data, which can be used to...


January 2024

Integrated heterodyne laser Doppler vibrometer based on stress-optic frequency shift in silicon nitride

Adam Raptakis, Christos Kouloumentas, Norbert Keil, Moritz Kleinert, Hercules Avramopoulos, Panos Groumas, Lefteris Gounaridis, Christos Tsokos, Rene G. Heidemann, Madeleine Weigel, Efstathios Andrianopoulos, Jörn P. Epping, Thi Lan Anh Tran, Thomas Aukes, Marco Wolfer, Alexander Draebenstedt, Nikos Lyras, Dimitrios Nikolaidis, Elias Mylonas, Nikolaos Baxevanakis, Roberto Pessina, Erik Schreuder, Matthijn Dekkers, Volker Seyfried

We demonstrate a compact heterodyne Laser Doppler Vibrometer (LDV) based on the realization of optical frequency shift in the silicon nitride photonic integration ! platform (TriPleX). The system comprises a dual-polarization coherent detector...


January 2024

Hybrid integration of Polymer PICs and InP optoelectronics for WDM and SDM terabit intra-DC optical interconnects

Efstathios Andrianopoulos, Christos Kouloumentas, Patrick Runge, Norbert Keil, Martin Moehrle, Ute Troppenz, Annachiara Pagano, David de Felipe Mesquida, Michael Theurer, Martin Kresse, Hercules Avramopoulos, Anna Chiado Piat, Panos Groumas, Christos Tsokos, Paraskevas Bakopoulos, Madeleine Weigel, Maria Massaouti, Zerihun Tegegne, Giorgos Megas

This paper presents a hybrid photonic integration concept based on the use of a polymer motherboard, InP EML arrays and InP PD arrays to realize WDM and SDM Terabit optical engines operating at 100-Gb/s or even at 20! 0-Gb/s per lane. The optical...



Items per page10ǀ20ǀ30
Results 21-30 of 283
<< < 1 2 3 4 5 6 7 8 > >>