Year: Author:

Heng Liu, Paul Zhang, Edward Chien, Justin Solomon, David Bommes

Despite high practical demand, algorithmic hexahedral meshing with guarantees on robustness and quality remains unsolved. A promising direction follows the idea of integer-grid maps, which pull back the Cartesian hexahedral grid formed by integer isoplanes from a parametric domain to a surface-conforming hexahedral mesh of the input object. Since directly optimizing for a high-quality integer-grid map is mathematically challenging, the construction is usually split into two steps: (1) generation of a surface-aligned octahedral field and (2) generation of an integer-grid map that best aligns to the octahedral field. The main robustness issue stems from the fact that smooth octahedral fields frequently exhibit singularity graphs that are not appropriate for hexahedral meshing and induce heavily degenerate integer-grid maps. The first contribution of this work is an enumeration of all local configurations that exist in hex meshes with bounded edge valence, and a generalization of the Hopf-Poincaré formula to octahedral fields, leading to necessary local and global conditions for the hex-meshability of an octahedral field in terms of its singularity graph. The second contribution is a novel algorithm to generate octahedral fields with prescribed hex-meshable singularity graphs, which requires the solution of a large non-linear mixed-integer algebraic system. This algorithm is an important step toward robust automatic hexahedral meshing since it enables the generation of a hex-meshable octahedral field.

Aljoša Ošep, Wolfgang Mehner, Paul Voigtlaender, Bastian Leibe
Accepted for IEEE Int. Conference on Robotics and Automation (ICRA'18), to appear

The most common paradigm for vision-based multi-object tracking is tracking-by-detection, due to the availability of reliable detectors for several important object categories such as cars and pedestrians. However, future mobile systems will need a capability to cope with rich human-made environments, in which obtaining detectors for every possible object category would be infeasible. In this paper, we propose a model-free multi-object tracking approach that uses a category-agnostic image segmentation method to track objects. We present an efficient segmentation mask-based tracker which associates pixel-precise masks reported by the segmentation. Our approach can utilize semantic information whenever it is available for classifying objects at the track level, while retaining the capability to track generic unknown objects in the absence of such information. We demonstrate experimentally that our approach achieves performance comparable to state-of-the-art tracking-by-detection methods for popular object categories such as cars and pedestrians. Additionally, we show that the proposed method can discover and robustly track a large variety of other objects.

» Show BibTeX

author = {O\v{s}ep, Aljo\v{s}a and Mehner, Wolfgang and Voigtlaender, Paul and Leibe, Bastian},
title = {Track, then Decide: Category-Agnostic Vision-based Multi-Object Tracking},
journal = {ICRA},
year = {2018}

Tassilo Kugelstadt, Dan Koschier, Jan Bender
Computer Graphics Forum (SCA)

In this paper we present a novel operator splitting approach for corotated FEM simulations. The deformation energy of the corotated linear material model consists of two additive terms. The first term models stretching in the individual spatial directions and the second term describes resistance to volume changes. By formulating the backward Euler time integration scheme as an optimization problem, we show that the first term is invariant to rotations. This allows us to use an operator splitting approach and to solve both terms individually with different numerical methods. The stretching part is solved accurately with an optimization integrator, which can be done very efficiently because the system matrix is constant over time such that its Cholesky factorization can be precomputed. The volume term is solved approximately by using the compliant constraints method and Gauss-Seidel iterations. Further, we introduce the analytic polar decomposition which allows us to speed up the extraction of the rotational part of the deformation gradient and to recover inverted elements. Finally, this results in an extremely fast and robust simulation method with high visual quality that outperforms standard corotated FEMs by more than two orders of magnitude and even the fast but inaccurate PBD and shape matching methods by more than one order of magnitude without having their typical drawbacks. This enables a very efficient simulation of complex scenes containing more than a million elements.

» Show BibTeX

author = {Tassilo Kugelstadt and Dan Koschier and Jan Bender},
title = {Fast Corotated FEM using Operator Splitting},
year = {2018},
journal = {Computer Graphics Forum (SCA)},
volume = {37},
number = {8}

Jan Bender, Dan Koschier, Tassilo Kugelstadt, Marcel Weiler
IEEE Transactions on Visualization and Computer Graphics

In this paper we introduce a novel micropolar material model for the simulation of turbulent inviscid fluids. The governing equations are solved by using the concept of Smoothed Particle Hydrodynamics (SPH). As already investigated in previous works, SPH fluid simulations suffer from numerical diffusion which leads to a lower vorticity, a loss in turbulent details and finally in less realistic results. To solve this problem we propose a micropolar fluid model. The micropolar fluid model is a generalization of the classical Navier-Stokes equations, which are typically used in computer graphics to simulate fluids. In contrast to the classical Navier-Stokes model, micropolar fluids have a microstructure and therefore consider the rotational motion of fluid particles. In addition to the linear velocity field these fluids also have a field of microrotation which represents existing vortices and provides a source for new ones. However, classical micropolar materials are viscous and the translational and the rotational motion are coupled in a dissipative way. Since our goal is to simulate turbulent fluids, we introduce a novel modified micropolar material for inviscid fluids with a non-dissipative coupling. Our model can generate realistic turbulences, is linear and angular momentum conserving, can be easily integrated in existing SPH simulation methods and its computational overhead is negligible. Another important visual feature of turbulent liquids is foam. Therefore, we present a post-processing method which considers microrotation in the foam particle generation. It works completely automatic and requires only one user-defined parameter to control the amount of foam.

» Show BibTeX

author = {Bender, Jan and Koschier, Dan and Kugelstadt, Tassilo and Weiler, Marcel},
title = {Turbulent Micropolar SPH Fluids with Foam},
journal = {IEEE Transactions on Visualization and Computer Graphics},
year = {2018},

Anne Gehre, Isaak Lim, Leif Kobbelt
Computer Graphics Forum (Proc. EUROGRAPHICS 2018)

Feature curves on 3D shapes provide important hints about significant parts of the geometry and reveal their underlying structure. However, when we process real world data, automatically detected feature curves are affected by measurement uncertainty, missing data, and sampling resolution, leading to noisy, fragmented, and incomplete feature curve networks. These artifacts make further processing unreliable. In this paper we analyze the global co-occurrence information in noisy feature curve networks to fill in missing data and suppress weakly supported feature curves. For this we propose an unsupervised approach to find meaningful structure within the incomplete data by detecting multiple occurrences of feature curve configurations (co-occurrence analysis). We cluster and merge these into feature curve templates, which we leverage to identify strongly supported feature curve segments as well as to complete missing data in the feature curve network. In the presence of significant noise, previous approaches had to resort to user input, while our method performs fully automatic feature curve co-completion. Finding feature reoccurrences however, is challenging since naive feature curve comparison fails in this setting due to fragmentation and partial overlaps of curve segments. To tackle this problem we propose a robust method for partial curve matching. This provides us with the means to apply symmetry detection methods to identify co-occurring configurations. Finally, Bayesian model selection enables us to detect and group re-occurrences that describe the data well and with low redundancy.

» Show BibTeX

title={Feature Curve Co-Completion in Noisy Data},
author={Gehre, Anne and Lim, Isaak and Kobbelt, Leif},
booktitle={Computer Graphics Forum},
organization={Wiley Online Library}

Marcel Weiler, Dan Koschier, Magnus Brand, Jan Bender
Computer Graphics Forum (Eurographics)

In this paper, we present a novel physically consistent implicit solver for the simulation of highly viscous fluids using the Smoothed Particle Hydrodynamics (SPH) formalism. Our method is the result of a theoretical and practical in-depth analysis of the most recent implicit SPH solvers for viscous materials. Based on our findings, we developed a list of requirements that are vital to produce a realistic motion of a viscous fluid. These essential requirements include momentum conservation, a physically meaningful behavior under temporal and spatial refinement, the absence of ghost forces induced by spurious viscosities and the ability to reproduce complex physical effects that can be observed in nature. On the basis of several theoretical analyses, quantitative academic comparisons and complex visual experiments we show that none of the recent approaches is able to satisfy all requirements. In contrast, our proposed method meets all demands and therefore produces realistic animations in highly complex scenarios. We demonstrate that our solver outperforms former approaches in terms of physical accuracy and memory consumption while it is comparable in terms of computational performance. In addition to the implicit viscosity solver, we present a method to simulate melting objects. Therefore, we generalize the viscosity model to a spatially varying viscosity field and provide an SPH discretization of the heat equation.

» Show BibTeX

author = {Marcel Weiler and Dan Koschier and Magnus Brand and Jan Bender},
title = {A Physically Consistent Implicit Viscosity Solver for SPH Fluids},
year = {2018},
journal = {Computer Graphics Forum (Eurographics)},
volume = {37},
number = {2}

Crispin Deul, Tassilo Kugelstadt, Marcel Weiler, Jan Bender
Computer Graphics Forum

In this paper, we present a novel direct solver for the efficient simulation of stiff, inextensible elastic rods within the Position-Based Dynamics (PBD) framework. It is based on the XPBD algorithm, which extends PBD to simulate elastic objects with physically meaningful material parameters. XPBD approximates an implicit Euler integration and solves the system of non-linear equations using a non-linear Gauss-Seidel solver. However, this solver requires many iterations to converge for complex models and if convergence is not reached, the material becomes too soft. In contrast we use Newton iterations in combination with our direct solver to solve the non-linear equations which significantly improves convergence by solving all constraints of an acyclic structure (tree), simultaneously. Our solver only requires a few Newton iterations to achieve high stiffness and inextensibility. We model inextensible rods and trees using rigid segments connected by constraints. Bending and twisting constraints are derived from the well-established Cosserat model. The high performance of our solver is demonstrated in highly realistic simulations of rods consisting of multiple ten-thousand segments. In summary, our method allows the efficient simulation of stiff rods in the Position-Based Dynamics framework with a speedup of two orders of magnitude compared to the original XPBD approach.

» Show BibTeX

author = {Crispin Deul and Tassilo Kugelstadt and Marcel Weiler and Jan Bender},
title = {Direct Position-Based Solver for Stiff Rods},
year = {2018},
journal = {Computer Graphics Forum},
volume = {37},
number = {6},
pages = {313-324},
keywords = {physically based animation, animation, Computing methodologies → Physical simulation},
doi = {10.1111/cgf.13326},
url = {},
eprint = {},

Liang-Chieh Chen, Alexander Hermans, George Papandreou, Florian Schroff, Peng Wang, Hartwig Adam
Conference on Computer Vision and Pattern Recognition (CVPR'18)

In this work, we tackle the problem of instance segmentation, the task of simultaneously solving object detection and semantic segmentation. Towards this goal, we present a model, called MaskLab, which produces three outputs: box detection, semantic segmentation, and direction prediction. Building on top of the Faster-RCNN object detector, the predicted boxes provide accurate localization of object instances. Within each region of interest, MaskLab performs foreground/background segmentation by combining semantic and direction prediction. Semantic segmentation assists the model in distinguishing between objects of different semantic classes including background, while the direction prediction, estimating each pixel's direction towards its corresponding center, allows separating instances of the same semantic class. Moreover, we explore the effect of incorporating recent successful methods from both segmentation and detection (i.e. atrous convolution and hypercolumn). Our proposed model is evaluated on the COCO instance segmentation benchmark and shows comparable performance with other state-of-art models.

» Show BibTeX

title = {{MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features}},
author = {Chen, Liang-Chieh and Hermans, Alexander and Papandreou, George and Schroff, Florian and Wang, Peng and Adam, Hartwig},
journal = {{IEEE Conference on Computer Vision and Pattern Recognition (CVPR'18)}},,
year = {2018}

Anne Gehre, Michael Bronstein, Leif Kobbelt, Justin Solomon
Eurographics Symposium on Geometry Processing 2018

Functional maps have gained popularity as a versatile framework for representing intrinsic correspondence between 3D shapes using algebraic machinery. A key ingredient for this framework is the ability to find pairs of corresponding functions (typically, feature descriptors) across the shapes. This is a challenging problem on its own, and when the shapes are strongly non-isometric, nearly impossible to solve automatically. In this paper, we use feature curve correspondences to provide flexible abstractions of semantically similar parts of non-isometric shapes. We design a user interface implementing an interactive process for constructing shape correspondence, allowing the user to update the functional map at interactive rates by introducing feature curve correspondences. We add feature curve preservation constraints to the functional map framework and propose an efficient numerical method to optimize the map with immediate feedback. Experimental results show that our approach establishes correspondences between geometrically diverse shapes with just a few clicks.

» Show BibTeX

author = "Gehre, Anne and Bronstein, Michael and Kobbelt, Leif and Solomon, Justin",
title = "Interactive Curve Constrained Functional Maps",
journal = "Computer Graphics Forum",
volume = 37,
number = 5,
year = 2018

Jens Cornelis, Jan Bender, Christoph Gissler, Markus Ihmsen, Matthias Teschner
The Visual Computer

Incompressible SPH (ISPH) is a promising concept for the pressure computation in SPH. It works with large timesteps and the underlying pressure Poisson equation (PPE) can be solved very efficiently. Still, various aspects of current ISPH formulations can be optimized.

This paper discusses issues of the two standard source terms that are typically employed in PPEs, i.e. density invariance (DI) and velocity divergence (VD). We show that the DI source term suffers from significant artificial viscosity, while the VD source term suffers from particle disorder and volume loss.

As a conclusion of these findings, we propose a novel source term handling. A first PPE is solved with the VD source term to compute a divergence-free velocity field with minimized artificial viscosity. To address the resulting volume error and particle disorder, a second PPE is solved to improve the sampling quality. The result of the second PPE is used for a particle shift (PS) only. The divergence-free velocity field - computed from the first PPE - is not changed, but only resampled at the updated particle positions. Thus, the proposed source term handling incorporates velocity divergence and particle shift (VD+PS).

» Show BibTeX

author = {Cornelis, Jens and Bender, Jan and Gissler, Christoph and Ihmsen, Markus and Teschner, Matthias},
title = {An optimized source term formulation for incompressible SPH},
journal = {The Visual Computer},
year = {2018},
month = {Feb},
issn = {1432-2315},
day = {20},
doi = {10.1007/s00371-018-1488-8},
url = {},

Andrea Bönsch, Sina Radke, Heiko Overath, Laura Marie Aschè, Jonathan Wendt, Tom Vierjahn, Ute Habel, Torsten Wolfgang Kuhlen
Proceedings of the IEEE Virtual Reality Conference, 2018

Personal space (PS), the flexible protective zone maintained around oneself, is a key element of everyday social interactions. It, e.g., affects people's interpersonal distance and is thus largely involved when navigating through social environments. However, the PS is regulated dynamically, its size depends on numerous social and personal characteristics and its violation evokes different levels of discomfort and physiological arousal. Thus, gaining more insight into this phenomenon is important.

We contribute to the PS investigations by presenting the results of a controlled experiment in a CAVE, focusing on German males in the age of 18 to 30 years. The PS preferences of 27 participants have been sampled while they were approached by either a single embodied, computer-controlled virtual agent (VA) or by a group of three VAs. In order to investigate the influence of a VA's emotions, we altered their facial expression between angry and happy. Our results indicate that the emotion as well as the number of VAs approaching influence the PS: larger distances are chosen to angry VAs compared to happy ones; single VAs are allowed closer compared to the group. Thus, our study is a foundation for social and behavioral studies investigating PS preferences.

» Show BibTeX

author = {Andrea B\"{o}nsch and Sina Radke and Heiko Overath and Laura M. Asch\'{e} and Jonathan Wendt and Tom Vierjahn and Ute Habel and Torsten W. Kuhlen},
title = {{Social VR: How Personal Space is Affected by Virtual Agents’ Emotions}},
booktitle = {Proceedings of IEEE Virtual Reality Conference 2018},
year = {2018}

Patric Schmitz, Julian Romeo Hildebrandt, André Calero Valdez, Leif Kobbelt, Martina Ziefle
IEEE Transactions on Visualization and Computer Graphics

In virtual environments, the space that can be explored by real walking is limited by the size of the tracked area. To enable unimpeded walking through large virtual spaces in small real-world surroundings, redirection techniques are used. These unnoticeably manipulate the user’s virtual walking trajectory. It is important to know how strongly such techniques can be applied without the user noticing the manipulation—or getting cybersick. Previously, this was estimated by measuring a detection threshold (DT) in highly-controlled psychophysical studies, which experimentally isolate the effect but do not aim for perceived immersion in the context of VR applications. While these studies suggest that only relatively low degrees of manipulation are tolerable, we claim that, besides establishing detection thresholds, it is important to know when the user’s immersion breaks. We hypothesize that the degree of unnoticed manipulation is significantly different from the detection threshold when the user is immersed in a task. We conducted three studies: a) to devise an experimental paradigm to measure the threshold of limited immersion (TLI), b) to measure the TLI for slowly decreasing and increasing rotation gains, and c) to establish a baseline of cybersickness for our experimental setup. For rotation gains greater than 1.0, we found that immersion breaks quite late after the gain is detectable. However, for gains lesser than 1.0, some users reported a break of immersion even before established detection thresholds were reached. Apparently, the developed metric measures an additional quality of user experience. This article contributes to the development of effective spatial compression methods by utilizing the break of immersion as a benchmark for redirection techniques.

Sebastian Freitag, Benjamin Weyers, Torsten Wolfgang Kuhlen
Proceedings of IEEE Virtual Reality Conference 2018

During free exploration of an unknown virtual scene, users often miss important parts, leading to incorrect or incomplete environment knowledge and a potential negative impact on performance in later tasks. This is addressed by wayfinding aids such as compasses, maps, or trails, and automated exploration schemes such as guided tours. However, these approaches either do not actually ensure exploration success or take away control from the user.

Therefore, we present an interactive assistance interface to support exploration that guides users to interesting and unvisited parts of the scene upon request, supplementing their own, free exploration. It is based on an automated analysis of object visibility and viewpoint quality and is therefore applicable to a wide range of scenes without human supervision or manual input. In a user study, we found that the approach improves users' knowledge of the environment, leads to a more complete exploration of the scene, and is also subjectively helpful and easy to use.

Jonathan Wendt, Benjamin Weyers, Andrea Bönsch, Jonas Stienen, Tom Vierjahn, Michael Vorländer, Torsten Wolfgang Kuhlen
IEEE Virtual Humans and Crowds for Immersive Environments (VHCIE), 2018

When interacting and communicating with virtual agents in immersive environments, the agents’ behavior should be believable and authentic. Thereby, one important aspect is a convincing auralizations of their speech. In this work-in progress paper a study design to evaluate the effect of adding directivity to speech sound source on the perceived social presence of a virtual agent is presented. Therefore, we describe the study design and discuss first results of a prestudy as well as consequential improvements of the design.

Daniel Zielasko, Alexander Meißner, Sebastian Freitag, Benjamin Weyers, Torsten Wolfgang Kuhlen
IEEE Virtual Reality Workshop on Everyday Virtual Reality 2018

Various factors influence the degree of cybersickness a user can suffer in an immersive virtual environment, some of which can be controlled without adapting the virtual environment itself. When using HMDs, one example is the size of the field of view. However, the degree to which factors like this can be manipulated without affecting the user negatively in other ways is limited. Another prominent characteristic of cybersickness is that it affects individuals very differently. Therefore, to account for both the possible disruptive nature of alleviating factors and the high interpersonal variance, a promising approach may be to intervene only in cases where users experience discomfort symptoms, and only as much as necessary. Thus, we conducted a first experiment, where the field of view was decreased when people feel uncomfortable, to evaluate the possible positive impact on sickness and negative influence on presence. While we found no significant evidence for any of these possible effects, interesting further results and observations were made.

» Show BibTeX

title={{Dynamic Field of View Reduction Related to Subjective Sickness Measures in an HMD-based Data Analysis Task}},
author={Zielasko, Daniel and Mei{\ss}ner, Alexander and Freitag Sebastian and Weyers, Benjamin and Kuhlen, Torsten W},
booktitle ={Proc. of IEEE Virtual Reality Workshop on Everyday Virtual Reality},

Andrea Bönsch
Doctoral Consortium at IEEE Virtual Reality Conference 2018

My research focuses on social locomotion of computer-controlled, human-like, virtual agents in virtual reality applications. Two main areas are covered in the literature: a) user-agent-dynamics in, e.g., pedestrian scenarios and b) pure inter-agent-dynamics. However, joint locomotion of a social group consisting of a user and one to several virtual agents has not been investigated yet. I intend to close this gap by contributing an algorithmic model of an agent’s behavior during social locomotion. In addition, I plan to evaluate the effects of the resulting agent’s locomotion patterns on a user’s perceived degree of immersion, comfort, as well as social presence.

» Show BibTeX

author = {Andrea B\"{o}nsch},
title = {Locomotion with Virtual Agents in the Realm of Social Virtual Reality},
booktitle = {Doctoral Consortium at IEEE Virtual Reality Conference 2018},
year = {2018}

Andrea Bönsch, Sina Radke, Jonathan Wendt, Tom Vierjahn, Ute Habel, Torsten Wolfgang Kuhlen
IEEE Virtual Humans and Crowds for Immersive Environments (VHCIE), 2018

The concept of personal space is a key element of social interactions. As such, it is a recurring subject of investigations in the context of research on proxemics. Using virtual-reality-based experiments, we contribute to this area by evaluating the direct effects of emotional expressions of an approaching virtual agent on an individual’s behavioral and physiological responses. As a pilot study focusing on the emotion expressed solely by facial expressions gave promising results, we now present a study design to gain more insight.

» Show BibTeX

author = {Andrea B\"{o}nsch and Sina Radke and Jonathan Wendt and Tom Vierjahn and Ute Habel and Torsten W. Kuhlen},
title = {{Towards Understanding the Influence of a Virtual Agent’s Emotional Expression on Personal Space}},
booktitle = {IEEE Virtual Humans and Crowds for Immersive Environments},
year = {2018}

Sevinc Eroglu, Sascha Gebhardt, Patric Schmitz, Dominik Rausch, Torsten Wolfgang Kuhlen
Proceedings of IEEE Virtual Reality 2018

Fluid artwork refers to works of art based on the aesthetics of fluid motion, such as smoke photography, ink injection into water, and paper marbling. Inspired by such types of art, we created Fluid Sketching as a novel medium for creating 3D fluid artwork in immersive virtual environments. It allows artists to draw 3D fluid-like sketches and manipulate them via six degrees of freedom input devices. Different sets of brush strokes are available, varying different characteristics of the fluid. Because of fluid's nature, the diffusion of the drawn fluid sketch is animated, and artists have control over altering the fluid properties and stopping the diffusion process whenever they are satisfied with the current result. Furthermore, they can shape the drawn sketch by directly interacting with it, either with their hand or by blowing into the fluid. We rely on particle advection via curl-noise as a fast procedural method for animating the fluid flow.

» Show BibTeX

author = {Eroglu, Sevinc and Gebhardt, Sascha and Schmitz, Patric and Rausch, Dominik and Kuhlen, Torsten Wolfgang},
title = {{Fluid Sketching — Immersive Sketching Based on Fluid Flow}},
booktitle = {Proceedings of IEEE Virtual Reality Conference 2018},
year = {2018}

Julian Romeo Hildebrandt, Patric Schmitz, André Calero Valdez, Leif Kobbelt, Martina Ziefle
Proceedings of HCI International 2018

Cybersickness poses a crucial threat to applications in the domain of Virtual Reality. Yet, its predictors are insufficiently explored when redirection techniques are applied. Those techniques let users explore large virtual spaces by natural walking in a smaller tracked space. This is achieved by unnoticeably manipulating the user’s virtual walking trajectory. Unfortunately, this also makes the application more prone to cause Cybersickness. We conducted a user study with a semi-structured interview to get quantitative and qualitative insights into this domain. Results show that Cybersickness arises, but also eases ten minutes after the exposure. Quantitative results indicate that a tolerance towards Cybersickness might be related to self-efficacy constructs and therefore learnable or trainable, while qualitative results indicate that users’ endurance of Cybersickness is dependent on symptom factors such as intensity and duration, as well as factors of usage context and motivation. The role of Cybersickness in Virtual Reality environments is discussed in terms of the applicability of redirected walking techniques.

Patric Schmitz, Leif Kobbelt
Mensch und Computer 2018 - Workshopband - Demo-Kurzbeitrag

Real walking is the most natural and intuitive way to navigate the world around us. In Virtual Reality, the limited tracking area of commercially available systems typically does not match the size of the virtual environment we wish to explore. Spatial compression methods enable the user to walk further in the virtual environment than the real tracking bounds permit. This demo gives a glimpse into our ongoing research on spatial compression in VR. Visitors can walk through a realistic model of the Aachen Cathedral within a room-sized tracking area.

Sabarinath Mahadevan, Paul Voigtlaender, Bastian Leibe

Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.

Stefan Breuers, Lucas Beyer, Umer Rafi, Bastian Leibe
Accepted for IEEE Int. Conference on Intelligent Robots and Systems (IROS'18), to appear

TL;DR: Detection+Tracking+{head orientation,skeleton} analysis. Smooth per-track enables filtering outliers as well as a "free flight" mode where expensive analysis modules are run with a stride, dramatically increasing runtime performance at almost no loss of prediction quality.

In the past decade many robots were deployed in the wild, and people detection and tracking is an important component of such deployments. On top of that, one often needs to run modules which analyze persons and extract higher level attributes such as age and gender, or dynamic information like gaze and pose. The latter ones are especially necessary for building a reactive, social robot-person interaction.

In this paper, we combine those components in a fully modular detection-tracking-analysis pipeline, called DetTA. We investigate the benefits of such an integration on the example of head and skeleton pose, by using the consistent track ID for a temporal filtering of the analysis modules’ observations, showing a slight improvement in a challenging real-world scenario. We also study the potential of a so-called “free-flight” mode, where the analysis of a person attribute only relies on the filter’s predictions for certain frames. Here, our study shows that this boosts the runtime dramatically, while the prediction quality remains stable. This insight is especially important for reducing power consumption and sharing precious (GPU-)memory when running many analysis components on a mobile platform, especially so in the era of expensive deep learning methods.

» Show BibTeX

title = {{Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline}},
author = {Breuers*, Stefan and Beyer*, Lucas and Rafi, Umer and Leibe, Bastian},
journal = {arXiv preprint arXiv:TBD},
year = {2018}

Lucas Beyer, Alexander Hermans, Timm Linder, Kai Oliver Arras, Bastian Leibe
arXiv:1804.02463 (IROS Submission)

TL;DR: Extend the DROW dataset to persons, extend the method to include short temporal context, and extensively benchmark all available methods.

Detecting humans is a key skill for mobile robots and intelligent vehicles in a large variety of applications. While the problem is well studied for certain sensory modalities such as image data, few works exist that address this detection task using 2D range data. However, a widespread sensory setup for many mobile robots in service and domestic applications contains a horizontally mounted 2D laser scanner. Detecting people from 2D range data is challenging due to the speed and dynamics of human leg motion and the high levels of occlusion and self-occlusion particularly in crowds of people. While previous approaches mostly relied on handcrafted features, we recently developed the deep learning based wheelchair and walker detector DROW. In this paper, we show the generalization to people, including small modifications that significantly boost DROW's performance. Additionally, by providing a small, fully online temporal window in our network, we further boost our score. We extend the DROW dataset with person annotations, making this the largest dataset of person annotations in 2D range data, recorded during several days in a real-world environment with high diversity. Extensive experiments with three current baseline methods indicate it is a challenging dataset, on which our improved DROW detector beats the current state-of-the-art.

» Show BibTeX

title = {{Deep Person Detection in 2D Range Data}},
author = {Beyer, Lucas and Hermans, Alexander and Linder, Timm and Arras, Kai Oliver and Leibe, Bastian},
journal = {arXiv preprint arXiv:1804.02463},
year = {2018}

Andreas Tillmann

We investigate the NP-hard problem of computing the spark of a matrix (i.e., the smallest number of linearly dependent columns), a key parameter in compressed sensing and sparse signal recovery. To that end, we identify polynomially solvable special cases, gather upper and lower bounding procedures, and propose several exact (mixed-)integer programming models and linear programming heuristics. In particular, we develop a branch-and-cut scheme to determine the girth of a matroid, focussing on the vector matroid case, for which the girth is precisely the spark of the representation matrix. Extensive numerical experiments demonstrate the effectiveness of our specialized algorithms compared to general-purpose black-box solvers applied to several mixed-integer programming models.

Code and test instances available per request; will become directly available on this page in the near future.
» Show BibTeX

author = {Andreas M. Tillmann},
title = {{Computing the Spark: Mixed-Integer Programming\\for the (Vector) Matroid Girth Problem}},
institution = {{RWTH Aachen University, Aachen, Germany}},
year = {2018}

Tobias Fischer, Ganapati Hegde, Frederic Matter, Marius Pesavento, Marc Pfetsch, Andreas Tillmann
to appear in Proc. WSA (ITG Workshop on Smart Antennas) 2018

In this paper, we consider the problem of joint antenna selection and analog beamformer design in a downlink single-group multicast network. Our objective is to reduce the hardware requirement by minimizing the number of required phase shifters at the transmitter while fulfilling given quality of constraints. We formulate the problem as an L0 minimization problem and devise a novel branch-and-cut based algorithm to solve the formulated mixed-integer nonlinear program optimally. We also propose a suboptimal heuristic algorithm to solve the above problem with a low computational complexity. Furthermore, the performance of the suboptimal method is evaluated against the developed optimal method, which serves as a benchmark.

» Show BibTeX

author = {T. Fischer and G. Hedge and F. Matter and M. Pesavento and M. E. Pfetsch and A. M. Tillmann},
title = {{Joint Antenna Selection and Phase-Only Beam Using Mixed-Integer Nonlinear Programming}},
booktitle = {{Proc. WSA 2018}},
pages = {},
year = {2018},
note = {to appear}

Aljoša Ošep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe

We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform. We propose a fully automatic approach for object mining from video which builds upon a generic object tracking approach. By applying this method to three large video datasets from autonomous driving and mobile robotics scenarios, we demonstrate its robustness and generality. Based on the object mining results, we propose a novel approach for unsupervised object discovery by appearance-based clustering. We show that this approach successfully discovers interesting objects relevant to driving scenarios. In addition, we perform self-supervised detector adaptation in order to improve detection performance on the KITTI dataset for existing categories. Our approach has direct relevance for enabling large-scale object learning for autonomous driving.

» Show BibTeX

title={Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video},
author={Aljo\v{s}a O\v{s}ep and Paul Voigtlaender and Jonathon Luiten and Stefan Breuers and Bastian Leibe},
journal={arXiv preprint arXiv:1712.08832},

Previous Year (2017)
Disclaimer Home Visual Computing institute RWTH Aachen University