1 code implementation • 16 Apr 2024 • Niklas Gard, Anna Hilsmann, Peter Eisert
In this paper, we present SPVLoc, a global indoor localization method that accurately determines the six-dimensional (6D) camera pose of a query image and requires minimal scene-specific prior knowledge and no scene-specific training.
no code implementations • 16 Apr 2024 • Florian Barthel, Arian Beckmann, Wieland Morgenstern, Anna Hilsmann, Peter Eisert
By training a decoder that maps implicit NeRF representations to explicit 3D Gaussian Splatting attributes, we can integrate the representational diversity and quality of 3D GANs into the ecosystem of 3D Gaussian Splatting for the first time.
no code implementations • 7 Mar 2024 • Wolfgang Paier, Paul Hinzer, Anna Hilsmann, Peter Eisert
We present a new approach for video-driven animation of high-quality neural 3D head models, addressing the challenge of person-independent animation from video input.
1 code implementation • CVPR Workshop on Event-based Vision 2023 • Wieland Morgenstern, Niklas Gard, Simon Baumann, Anna Hilsmann, Peter Eisert
We present a new approach to direct depth estimation for Spatial Augmented Reality (SAR) applications using event cameras.
no code implementations • 21 Dec 2023 • Eric L. Wisotzky, Lara Wallburg, Anna Hilsmann, Peter Eisert, Thomas Wittenberg, Stephan Göb
This results in long training periods of such deep networks and the size of the networks is huge.
1 code implementation • 19 Dec 2023 • Wieland Morgenstern, Florian Barthel, Anna Hilsmann, Peter Eisert
In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering.
no code implementations • 15 Dec 2023 • Eric L. Wisotzky, Jost Triller, Anna Hilsmann, Peter Eisert
To address these drawbacks, we present a novel approach combining two calibrated multispectral real-time capable snapshot cameras, covering different spectral ranges, into a stereo-system.
no code implementations • 13 Dec 2023 • Clemens Seibold, Anna Hilsmann, Peter Eisert
Furthermore, we show that our approach does not impair the biometric quality, which is essential for high quality morphs.
1 code implementation • 8 Dec 2023 • Florian Barthel, Anna Hilsmann, Peter Eisert
Current 3D GAN inversion methods for human heads typically use only one single frontal image to reconstruct the whole 3D head model.
1 code implementation • 25 Nov 2023 • Luan Wei, Anna Hilsmann, Peter Eisert
We introduce SOLOPlanes, a real-time planar reconstruction model based on a modified instance segmentation architecture which simultaneously predicts semantics for each plane instance, along with plane parameters and piece-wise plane instance masks.
no code implementations • 6 Nov 2023 • Paul Knoll, Wieland Morgenstern, Anna Hilsmann, Peter Eisert
The extension to a controllable synthesis of dynamic human performances poses an exciting research question.
no code implementations • 11 Oct 2023 • Karam Dawoud, Wojciech Samek, Peter Eisert, Sebastian Lapuschkin, Sebastian Bosse
In the ever-evolving field of Artificial Intelligence, a critical challenge has been to decipher the decision-making processes within the so-called "black boxes" in deep learning.
no code implementations • 5 Oct 2023 • Wieland Morgenstern, Milena T. Bagdasarian, Anna Hilsmann, Peter Eisert
We propose a novel representation of virtual humans for highly realistic real-time animation and rendering in 3D applications.
no code implementations • 31 Aug 2023 • Johannes Künzel, Anna Hilsmann, Peter Eisert
We introduce BTSeg, an innovative, semi-supervised training approach enhancing semantic segmentation models in order to effectively handle a range of adverse conditions without requiring the creation of extensive new datasets.
no code implementations • 25 Jun 2023 • Michael Gerstenberger, Steffen Maaß, Peter Eisert, Sebastian Bosse
We introduce a Gaussian Prototype Layer for gradient-based prototype learning and demonstrate two novel network architectures for explainable segmentation one of which relies on region proposals.
no code implementations • 16 Jun 2023 • Wolfgang Paier, Anna Hilsmann, Peter Eisert
This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering.
no code implementations • 2 Jun 2023 • Aleixo Cambeiro Barreiro, Mariusz Trzeciakiewicz, Anna Hilsmann, Peter Eisert
Digitalization of existing buildings and the creation of 3D BIM models for them has become crucial for many tasks.
no code implementations • 10 May 2023 • Jannes S. Magnusson, Anna Hilsmann, Peter Eisert
This work proposes a novel concept for tree and plant reconstruction by directly inferring a Lindenmayer-System (L-System) word representation from image data in an image captioning approach.
no code implementations • 9 May 2023 • Arian Beckmann, Anna Hilsmann, Peter Eisert
Due to the rising threat of deepfakes to security and privacy, it is most important to develop robust and reliable detectors.
no code implementations • 6 Mar 2023 • Johannes Künzel, Darko Vehar, Rico Nestler, Karl-Heinz Franke, Anna Hilsmann, Peter Eisert
The assessment of sewer pipe systems is a highly important, but at the same time cumbersome and error-prone task.
no code implementations • 28 Feb 2023 • Decai Chen, Haofei Lu, Ingo Feldmann, Oliver Schreer, Peter Eisert
Recent works represent the dynamic scene with neural radiance fields for photorealistic view synthesis, while their surface geometry is under-constrained and noisy.
1 code implementation • CVPR 2022 • Markus Worchel, Rodrigo Diaz, Weiwen Hu, Oliver Schreer, Ingo Feldmann, Peter Eisert
While flexible, neural surface representations are a significant bottleneck in optimization runtime.
no code implementations • 21 Nov 2022 • Eric L. Wisotzky, Charul Daudkhane, Anna Hilsmann, Peter Eisert
The dataset is a combination of real captured scenes with images from publicly available data adapted to the 4x4 mosaic pattern.
1 code implementation • 21 Nov 2022 • Decai Chen, Peng Zhang, Ingo Feldmann, Oliver Schreer, Peter Eisert
Recent works on implicit neural representations have made significant strides.
1 code implementation • 11 Oct 2022 • Niklas Gard, Anna Hilsmann, Peter Eisert
Applications in the field of augmented reality or robotics often require joint localisation and 6D pose estimation of multiple objects.
no code implementations • 29 Aug 2022 • Benjamin Kossack, Eric Wisotzky, Peter Eisert, Sebastian P. Schraven, Brigitta Globke, Anna Hilsmann
From the extracted signals, we derive the signal-to-noise ratio, magnitude in the frequency domain, heart rate, perfusion index as well as correlation between specific rPPG signals in order to locally assess the perfusion of a specific region of human tissue.
no code implementations • 18 Mar 2022 • Michael Gerstenberger, Sebastian Lapuschkin, Peter Eisert, Sebastian Bosse
It shows that even correct classifications can rely on unreasonable prototypes that result from confounding variables in a dataset.
no code implementations • 26 Feb 2022 • Decai Chen, Markus Worchel, Ingo Feldmann, Oliver Schreer, Peter Eisert
In this work, we enhance a professional end-to-end volumetric video production pipeline to achieve high-fidelity human body reconstruction using only passive cameras.
no code implementations • 7 Feb 2022 • Alexandra Zimmer, Anna Hilsmann, Wieland Morgenstern, Peter Eisert
In detail, we derive parameters of a sequence of body models, representing shape and motion of a person, including jaw poses, facial expressions, and finger poses.
no code implementations • 1 Feb 2022 • Clemens Seibold, Johannes Künzel, Anna Hilsmann, Peter Eisert
The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on pixel-precision.
Explainable Artificial Intelligence (XAI) Image Segmentation +3
no code implementations • 31 Jan 2022 • Niklas Gard, Anna Hilsmann, Peter Eisert
In this paper, we present a multi-object 6D detection and tracking pipeline for potentially similar and non-textured objects.
no code implementations • 30 Nov 2021 • Aleixo Cambeiro Barreiro, Clemens Seibold, Anna Hilsmann, Peter Eisert
Recently, the use of drones or helicopters for remote recording is increasing in the industry, sparing the technicians this perilous task.
no code implementations • 9 Aug 2021 • Maciej Janik, Niklas Gard, Anna Hilsmann, Peter Eisert
We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape.
no code implementations • 26 Mar 2021 • Clemens Seibold, Anna Hilsmann, Peter Eisert
This evaluation framework is based on removing detected artifacts and analyzing the influence of these changes on the decision of the DNN.
no code implementations • 4 Jan 2021 • Max Allan, Jonathan McLeod, Congcong Wang, Jean Claude Rosenthal, Zhenglei Hu, Niklas Gard, Peter Eisert, Ke Xue Fu, Trevor Zeffiro, Wenyao Xia, Zhanshi Zhu, Huoling Luo, Fucang Jia, Xiran Zhang, Xiaohong Li, Lalith Sharan, Tom Kurmann, Sebastian Schmid, Raphael Sznitman, Dimitris Psychogyios, Mahdi Azizian, Danail Stoyanov, Lena Maier-Hein, Stefanie Speidel
The stereo correspondence and reconstruction of endoscopic data sub-challenge was organized during the Endovis challenge at MICCAI 2019 in Shenzhen, China.
no code implementations • 22 Sep 2020 • Wolfgang Paier, Anna Hilsmann, Peter Eisert
We solve these problems by combining the realism and simplicity of example-based animations with the advantages of neural face models.
no code implementations • 2 Sep 2020 • Anna Hilsmann, Philipp Fechteler, Wieland Morgenstern, Wolfgang Paier, Ingo Feldmann, Oliver Schreer, Peter Eisert
Going beyond the application of free-viewpoint volumetric video, we allow re-animation and alteration of an actor's performance through (i) the enrichment of the captured data with semantics and animation properties and (ii) applying hybrid geometry- and video-based animation methods that allow a direct animation of the high-quality data itself instead of creating an animatable model that resembles the captured data.
no code implementations • 23 Apr 2020 • Clemens Seibold, Anna Hilsmann, Peter Eisert
A morphed face image is a synthetically created image that looks so similar to the faces of two subjects that both can use it for verification against a biometric verification system.
no code implementations • 11 Dec 2019 • Johannes Künzel, Thomas Werner, Ronja Möller, Peter Eisert, Jan Waschnewski, Ralf Hilpert
The task of detecting and classifying damages in sewer pipes offers an important application area for computer vision algorithms.
no code implementations • 5 Jul 2018 • Clemens Seibold, Anna Hilsmann, Peter Eisert
This map is compared with the highlights in the image that is suspected to be a fraud.
no code implementations • 11 Jun 2018 • Clemens Seibold, Wojciech Samek, Anna Hilsmann, Peter Eisert
Artificial neural networks tend to learn only what they need for a task.