43 citations · 116 across the 19 of their papers we have counts for
20 papers
Current Tomography -- Localization of void fractions in conducting liquids by measuring the induced magnetic flux density
L. Krause, N. Kumar, T. Wondrak +3
A novel concept of a measurement technology for the localization and determination of the size of gas bubbles is presented, which is intended to contribute to a further understandi…
Learning to reconstruct the bubble distribution with conductivity maps using Invertible Neural Networks and Error Diffusion
Nishant Kumar, Lukas Krause, Thomas Wondrak +3
Electrolysis is crucial for eco-friendly hydrogen production, but gas bubbles generated during the process hinder reactions, reduce cell efficiency, and increase energy consumption…
Towards Computational Performance Engineering for Unsupervised Concept Drift Detection -- Complexities, Benchmarking, Performance Analysis
Elias Werner, Nishant Kumar, Matthias Lieber +3
Concept drift detection is crucial for many AI systems to ensure the system's reliability. These systems often have to deal with large amounts of data or react in real-time. Thus,…
Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection
Nishant Kumar, Siniša Šegvić, Abouzar Eslami +1
Real-world deployment of reliable object detectors is crucial for applications such as autonomous driving. However, general-purpose object detectors like Faster R-CNN are prone to…
Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
David Bojanić, Kristijan Bartol, Josep Forest +3
Learning universal representations across different applications domain is an open research problem. In fact, finding universal architecture within the same application but across…
Enhancing Fairness of Visual Attribute Predictors
Tobias Hänel, Nishant Kumar, Dmitrij Schlesinger +4
The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We…
Parallel Compositing of Volumetric Depth Images for Interactive Visualization of Distributed Volumes at High Frame Rates
Aryaman Gupta, Pietro Incardona, Anton Brock +5
We present a parallel compositing algorithm for Volumetric Depth Images (VDIs) of large three-dimensional volume data. Large distributed volume data are routinely produced in both…
Efficient Raycasting of Volumetric Depth Images for Remote Visualization of Large Volumes at High Frame Rates
Aryaman Gupta, Ulrik Günther, Pietro Incardona +4
We present an efficient raycasting algorithm for rendering Volumetric Depth Images (VDIs), and we show how it can be used in a remote visualization setting with VDIs generated and…
Real-time Visualization of Stream-based Monitoring Data
Jan Baumeister, Bernd Finkbeiner, Stefan Gumhold +1
Stream-based runtime monitors are used in safety-critical applications such as Unmanned Aerial Systems (UAS) to compute comprehensive statistics and logical assessments of system h…
InFlow: Robust outlier detection utilizing Normalizing Flows
Nishant Kumar, Pia Hanfeld, Michael Hecht +3
Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while…
FuseVis: Interpreting neural networks for image fusion using per-pixel saliency visualization
Nishant Kumar, Stefan Gumhold
Image fusion helps in merging two or more images to construct a more informative single fused image. Recently, unsupervised learning based convolutional neural networks (CNN) have…
Visualisation of Medical Image Fusion and Translation for Accurate Diagnosis of High Grade Gliomas
Nishant Kumar, Nico Hoffmann, Matthias Kirsch +1
The medical image fusion combines two or more modalities into a single view while medical image translation synthesizes new images and assists in data augmentation. Together, these…
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
Aritra Bhowmik, Stefan Gumhold, Carsten Rother +1
We address a core problem of computer vision: Detection and description of 2D feature points for image matching. For a long time, hand-crafted designs, like the seminal SIFT algori…
Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift
Titus Leistner, Hendrik Schilling, Radek Mackowiak +2
We propose a method for depth estimation from light field data, based on a fully convolutional neural network architecture. Our goal is to design a pipeline which achieves highly a…
Structural Similarity based Anatomical and Functional Brain Imaging Fusion
Nishant Kumar, Nico Hoffmann, Martin Oelschlägel +3
Multimodal medical image fusion helps in combining contrasting features from two or more input imaging modalities to represent fused information in a single image. One of the pivot…
A Proposed Framework for Interactive Virtual Reality In Situ Visualization of Parallel Numerical Simulations
Aryaman Gupta, Ulrik Günther, Pietro Incardona +4
As computer simulations progress to increasingly complex, non-linear, and three-dimensional systems and phenomena, intuitive and immediate visualization of their results is becomin…
Analysis of the Near-Wall Flow in a Turbine Cascade by Splat Visualization
Baldwin Nsonga, Gerik Scheuermann, Stefan Gumhold +3
Turbines are essential components of jet planes and power plants. Therefore, their efficiency and service life are of central engineering interest. In the case of jet planes or the…
Global Hypothesis Generation for 6D Object Pose Estimation
Frank Michel, Alexander Kirillov, Eric Brachmann +4
This paper addresses the task of estimating the 6D pose of a known 3D object from a single RGB-D image. Most modern approaches solve this task in three steps: i) Compute local feat…
DSAC - Differentiable RANSAC for Camera Localization
Eric Brachmann, Alexander Krull, Sebastian Nowozin +4
RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines ha…
Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images
Alexander Krull, Eric Brachmann, Frank Michel +3
Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. T…