ATTENTION: This is a web archive! The IMS Group was split up in 2018 and does not exist anymore. Recent work of former members can be found at the VR/AR Group and the Computer Vision Group.

Interactive Media Systems, TU Wien


Publications Feed

Scientific publications, talks, and theses. Click a title or “Details” link to learn
more about a particular publication (including BibTeX, PDF download, etc).


Walking in Virtual Reality: Flexible Spaces and Other Techniques In many virtual reality applications the virtual world is larger than the available physical workspace. Multiple mechanical solutions have been… K. Vasylevska, I. Podkosova, H. Kaufmann Details
Advances in Embedded Computer Vision This illuminating collection offers a fresh look at the very latest advances in the field of embedded computer vision. Emerging areas covered by this… B. Kisacanin, M. Gelautz Details
Categorization and Machine Learning: The Modeling of Human Understanding in Computers Machine learning is the attempt to imitate human categorization of perceived reality in computers. It is driven by the desire to provide machines… H. Eidenberger Details
GeodiKon. Die Lernmaterialien Das Buch enthält mehr als 100 ausgewählte, erprobte und nach speziellen Kriterien zusammengestellte Raumvorstellungsübungen, durch die die… A. Asperl, C. Feßl, W. Gems, H. Kaufmann, S. Leopoldseder, G. Maresch, D. Miestinger, T. Müller, K. Luksch, G. Redl, K. Scheiber, G. Schilling, H. Schmied, H. Slepcevic, M. Wischounig Details


Age-group estimation in free-ranging African elephants based on acoustic cues of low-frequency rumbles A. Stöger, M. Zeppelzauer, A. Baotic: "Age-group estimation in free-ranging African elephants based on acoustic cues of low-frequency rumbles";… A. Stöger, M. Zeppelzauer, A. Baotic Details
Towards an automated acoustic detection system for free-ranging elephants M. Zeppelzauer, S. Hensman, A. Stöger: "Towards an automated acoustic detection system for free-ranging elephants"; Bioacoustics-The International… M. Zeppelzauer, S. Hensman, A. Stöger Details
Software ohne Gewähr Wer glaubt, dass der Markt allein den Preis einer Software bestimmt, der negiert wesentliche Aspekte des Rechtsgeschäfts… H. Eidenberger Details
Cooperative and asynchronous stereo vision for dynamic vision sensors Dynamic vision sensors (DVSs) encode visual input as a stream of events generated upon relative light intensity changes in the scene. These sensors… E. Piatkowska, A. Belbachir, M. Gelautz Details
Enhancement of sparse Silicon Retina-based stereo matching using Belief Propagation and Two-Stage Post-Filtering We present two improvement techniques for stereo matching algorithms using silicon retina sensors. We verify the results with ground truth data. In… J. Kogler, F. Eibensteiner, M. Humenberger, C. Sulzbachner, M. Gelautz, J. Scharinger Details
Vision-Based Long-Range 3D Tracking, applied to Underground Surveying Tasks To address the need of highly automated positioning systems in underground construction, we present a long-range 3D tracking system based on infrared… A. Mossel, G. Gerstweiler, E. Vonach, K. Chmelina, H. Kaufmann Details
SmartCopter - Enabling Autonomous Flight in Indoor Environments with a Smartphone as On-Board Processing Unit We present a low-cost Unmanned Aerial Vehicle (UAV) for autonomous flight and navigation in GPS-denied environments using an off-the-shelf smartphone… A. Mossel, M. Leichtfried, C. Kaltenriener, H. Kaufmann Details
Motion estimation and segmentation in depth and intensity videos This paper investigates motion estimation and segmentation of independently moving objects in video sequences that contain depth and intensity… S. Ghuffar, N. Brosch, N. Pfeifer, M. Gelautz Details


Efficient Depth Propagation in Videos with GPU-acceleration In this paper we propose an optimized semi-automatic approach for efficient 2D-to-3D video conversion. It is based on a conversion algorithm [1] that… M. Ivancsics, N. Brosch, M. Gelautz Details
ACTO: A Modular Actuated Tangible User Interface Object We introduce a customizable, reusable actuated tangible user interface object: ACTO. Its modular design allows quick adaptations for different… E. Vonach, G. Gerstweiler, H. Kaufmann Details
Development of Tests to Evaluate the Sensory Abilities of Children with Autism Spectrum Disorder using Touch and Force Sensors An emerging line of research that attempts to reveal underlying mechanisms of Autism Spectrum Disorder (ASD) studies differences in sensory… M. Riederer, C. Schönauer, H. Kaufmann, E. Söchting, C. Lamm Details
Multimodal Synchronization of Image Galleries This paper describes our contribution to the MediaEval 2014 task on the Synchronization of multi-user Event Media (SEM). We propose two multimodal… M. Zaharieva, M. Riegler, M. Fabro Details
Clustering and Retrieval of Social Events in Flickr This paper describes our contributions to the Social Event Detection (SED) task as part of the MediaEval Benchmark 2014. We first present an… M. Zaharieva, P. Schopfhauser, M. Fabro, M. Zeppelzauer Details
A Unified Framework for Retrieving Diverse Social Images In this paper we explore the performance of a generic, unified framework for the retrieval of relevant and diverse images from social photo… M. Zaharieva, P. Schwab Details
Gestalt Interest Points for Image Description in Weight-Invariant Face Recognition In this work, we propose two improvements of the Gestalt Interest Points (GIP) algorithm for the recognition of faces of people that have underwent… M. Hörhan, H. Eidenberger Details
Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation Motion in the image plane is ultimately a function of 3D motion in space. We propose to compute optical flow using what is ostensibly an extreme… M. Hornacek, F. Besse, J. Kautz, A. Fitzgibbon, C. Rother Details
Evaluation of LDR, Tone Mapped and HDR Stereo Matching Using Cost-volume Filtering Approach We present stereo matching solutions based on a fast costvolume filtering approach for High Dynamic Range (HDR) scenes. Multi-exposed stereo images… T. Akhavan, H. Yoo, M. Gelautz Details
Using TimeML to Support the Modeling of Computerized Clinical Guidelines The modeling of clinical guidelines in order to apply them in computerized medical tools is a challenging and laborious task. In this project we show… R. Wenzina, K. Kaiser Details
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs We take a new approach to computing dense scene flow between a pair of consecutive RGB-D frames. We exploit the availability of depth data by seeking… M. Hornacek, A. Fitzgibbon, C. Rother Details
Unsupervised selection of robust audio feature subsets Feature selection is applied to identify relevant and complementary features from a given high-dimensional feature set. In general, existing… G. Sageder, M. Zaharieva, M. Zeppelzauer Details
Evaluating RGB+D Hand Posture Detection Methods for Mobile 3D Interaction In mobile applications it is crucial to provide intuitive means for 2D and 3D interaction. A large number of techniques exist to support a natural… D. Fritz, A. Mossel, H. Kaufmann Details
Towards the Application of TimeML in Clinical Guidelines The modeling of computer-interpretable clinical guidelines is a laborious task. In this project we propose a two-step approach to explore whether the… R. Wenzina, K. Kaiser Details
Influence of Vertical Navigation Metaphors on Presence A sense of spatial presence as a feeling of "being there" is an important part of the virtual experience. Navigation is a fundamental task in virtual… K. Vasylevska, H. Kaufmann Details
Stereo HDR Disparity Map Computation Using Structured Light In this paper, we present work in progress towards the generation of a ground truth data set for High Dynamic Range (HDR) stereo matching. The… T. Akhavan, C. Kapeller, J. Cho, M. Gelautz Details
Depth Map Post-Processing for Depth-Image-Based Rendering: A User Study We analyse the impact of depth map post-processing techniques on the visual quality of stereo pairs that contain a novel view. To this end, we… M. Nezveda, N. Brosch, F. Seitner, M. Gelautz Details
Efficient quality enhancement of disparity maps based on alpha matting We propose an efficient disparity map enhancement method that improves the alignment of disparity edges and color edges even in the presence of mixed… N. Brosch, M. Nezveda, M. Gelautz, F. Seitner Details
Graph-based Similarity of Petroglyphs M. Seidl, E. Wieser, M. Zeppelzauer, A. Pinz, C. Breiteneder: "Graph-based Similarity of Petroglyphs"; in: "VISART "Where Computer Vision Meets… M. Seidl, E. Wieser, M. Zeppelzauer, A. Pinz, C. Breiteneder Details
The Effects of Direct and Global Illumination on Presence in Augmented Reality In this paper we present an experiment, which was designed and conducted with the goal to study the effect of lighting on the sense of presence in… P. Kán, A. Dünser, M. Billinghurst, C. Schönauer, H. Kaufmann Details
Real-Time Machine Guidance with Tracking Cameras Mining and tunneling processes are more and more automatized, mechanized and speeded up. Machines, such as roadheaders, jumbos, dredgers, loaders… K. Chmelina, E. Lammer, A. Mossel, H. Kaufmann Details
Echtzeitvermessung mit Infrarottrackingkameras - Untersuchung einer neuen Messtechnik für untertage K. Chmelina, A. Mossel, H. Kaufmann: "Echtzeitvermessung mit Infrarottrackingkameras - Untersuchung einer neuen Messtechnik für untertage"; in:… K. Chmelina, A. Mossel, H. Kaufmann Details


Landscape of Current Imaging Technology A. Mossel, R. Raskar: "Landscape of Current Imaging Technology"; Talk: Summer School on Advances in Imaging, MIT Media Lab (invited); 08-07-2014. A. Mossel, R. Raskar Details
What if ... Visions and Trends for Imaging Applications A. Mossel, R. Raskar: "What if ... Visions and Trends for Imaging Applications"; Talk: Summer School on Advances in Imaging, MIT Media Lab (invited);… A. Mossel, R. Raskar Details
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs (talk) M. Hornacek: "SphereFlow: 6 DoF Scene Flow from RGB-D Pairs (talk)"; Talk: EU-Korea Conference on Science and Technology, Wien (invited); 07-24-2014. M. Hornacek Details
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs (talk) M. Hornacek: "SphereFlow: 6 DoF Scene Flow from RGB-D Pairs (talk)"; Talk: Pattern Recognition and Computer Vision Colloquium, Prag, Tschechische… M. Hornacek Details
Locally Rigid RGB-D Scene Flow (talk) M. Hornacek: "Locally Rigid RGB-D Scene Flow (talk)"; Talk: Computer Vision Winter Workshop, Krtiny, Tschechische Republik; 02-03-2014. M. Hornacek Details


Depth-guided disocclusion inpainting for temporal consistent virtual view synthesis Depth Image Based Rendering (DIBR) has become an important tool in the field of free-viewpoint video and three-dimensional television as this… T. Rittler Details
Evaluation of depth map post-processing techniques for novel view generation Depth-Image-Based Rendering (DIBR) is a key technology for the processing and distribution of three-dimensional (3D) content. Given a two-dimensional… M. Nezveda Details
Intuitive und markerlose Interaktion in einer mobilen Virtual Reality Anwendung auf Basis von RGBD-Daten The diploma thesis discusses touchless interaction techniques on handheld devices to intuitively manipulate a virtual 3D scene that is presented to… D. Fritz Details
Robust Wide-Area Tracking and Intuitive 3D Interaction for Mixed Reality Environments Mixed reality has been a focus of research for many years and has recently gained particular importance with the emergence of powerful, low-cost… A. Mossel Details
High-Quality Real-Time Global Illumination in Augmented Reality High-quality image synthesis, indistinguishable from reality, has been one of the most important problems in computer graphics from its beginning.… P. Kán Details
Effiziente Tiefenpropagierung in Videos mit GPU-Unterstützung The commercial availability of stereoscopic displays increases the demand for 3D content. Therefore, fast and robust tools for the generation of such… M. Ivancsics Details