Image and Video Analysis & Synthesis

Contact: Margrit Gelautz

Our group performs basic and applied research on image and video analysis & synthesis with a focus on 3D scene reconstruction (especially, stereo analysis), video object segmentation, image matting and motion estimation. Current research activities concentrate on the application fields of assisted/autonomous driving and motion studies for human-robot interaction.

2019

Conferences

Semi-automatic post-processing of multi-view 2D-plus-depth video We propose a post-processing framework based on multiview interactive video segmentation for correcting 2D-plus-depth video footage. The suggested…	B. Sespede, F. Seitner, M. Gelautz	Details
SLAMANTIC - Leveraging Semantics to Improve VSLAM in Dynamic Environments In this paper, we tackle the challenge for VSLAM of handling nonstatic environments. We propose to include semantic information obtained by deep…	M. Schörghuber, D. Steininger, Y. Carbon, M. Gelautz	Details
Evaluation Study on Semantic Object Labelling in Street Scenes We present a processing pipeline for semantic scene labelling that was developed in view of autonomous driving applications. Our study focuses on two…	A. Wittmann, M. Gelautz, F. Seitner	Details

Talks

Visual Computing in Autonomous Driving and Human-Robot Interaction	M. Gelautz	Details
Digital Observation of Human Motion, Expression, and Intention Die Entwicklung von Algorithmen und Softwarewerkzeugen zur Beobachtung und automatischen Interpretation von menschlicher Bewegung durch Videoanalyse…	M. Gelautz	Details
Computer Vision Trends - Autonomous Driving and Human-Robot Interaction In recent years, computer vision research has been strongly influenced by latest developments in the fields of artificial intelligence and deep…	M. Gelautz	Details
Body Language in Human‐Robot Interaction D. Stoeva: "Body Language in Human‐Robot Interaction"; Poster: Summer School TrustRobots 2019, Wien; 15.09.2019 - 20.09.2019.	D. Stoeva	Details
Camera-Based In-Cabin Monitoring - Applications and Business Cases M. Gelautz: "Camera-Based In-Cabin Monitoring - Applications and Business Cases"; Vortrag: Forum Automatisierte Mobilität, Wien (eingeladen);…	M. Gelautz	Details
Body Language in Human‐Robot Interaction	M. Gelautz, D. Stoeva, D. Schörkhuber	Details

Theses

Semantic Labelling of Objects in Street Scenes An automatic and robust semantic interpretation of street scenes is required in order to improve driving assistance systems and to reach fully…

A. Wittmann

3D Visual Content Datasets Development and performance evaluation of efficient methods for coding, transmission, and quality assessment of 3D visual content require rich…	K. Fliegel, F. Battisti, M. Carli, M. Gelautz, L. Krasula, P. Le-Callet, V. Zlokolica	Details
Quality of Experience and Quality of Service Metrics for 3D Content Traditionally, the quality of a multimedia system was mainly assessed through the evaluation of its Quality of Service (QoS) that is by evaluating…	M. Barreda-Angeles, F. Battisti, G. Boato, M. Carli, E. Dumic, M. Gelautz, C. Hewage, P. Le-Callet, A. Liotta, C. Pasquini, A. Pereda-Baños, C. Politis, D. Sandic, M. Tekalp, M. Torres-Vega, V. Zlokolica	Details

An End-to-end System for Real-Time Point Cloud Visualization The growing availability of RGB-D data, as delivered by current depth sensing devices, forms the basis for a variety of mixed reality (MR)…	H. Hofer, F. Seitner, M. Gelautz	Details
Vision-based Autonomous Feeding Robot This paper tackles the problem of vision-based indoor navigation for robotic platforms. Contrary to methods using adaptions of the infrastructure…	M. Schörghuber, M. Wallner, R. Jung, M. Humenberger, M. Gelautz	Details
A workflow for 3D model reconstruction from multi-view depth acquisitions of dynamic scenes We propose a workflow for generating highquality 3D models of dynamic scenes for the film and entertainment industry. Our 3D scanning system…	C. Kapeller, B. Sespede, M. Nezveda, M. Labschütz, S. Flöry, F. Seitner, M. Gelautz	Details

An Evaluation Framework for Dynamic Scene Acquisitions Using Multiple Stereo Cameras C. Kapeller, B. Sespede, M. Nezveda, M. Labschütz, S. Flöry, F. Seitner, M. Gelautz: "An Evaluation Framework for Dynamic Scene Acquisitions Using…	C. Kapeller, B. Sespede, M. Nezveda, M. Labschütz, S. Flöry, F. Seitner, M. Gelautz	Details
A Post-processing Tool for Multi-view 2D-plus-depth Video B. Sespede, F. Seitner, M. Gelautz: "A Post-processing Tool for Multi-view 2D-plus-depth Video"; Poster: The 15th ACM SIGGRAPH European Conference on…	B. Sespede, F. Seitner, M. Gelautz	Details
Camera-based pose estimation in dynamic environments - concept and status This PhD tackles the challenge of camera-based methods for navigation and environmental sensing in dynamic environments. The goal is to design a…	M. Schörghuber, M. Humenberger, M. Gelautz	Details

Asynchronous Stereo Vision Event-driven Stereo Matching and Tracking for Dynamic Vision Sensors This thesis addresses the problem of stereo reconstruction from a stream of events provided by two dynamic vision sensors (DVS) in a stereo…	E. Piatkowska	Details
Techniques for Improving Mobile Video Creation In this thesis, we explore methods to assist non-professional users with video creation on mobile devices. The developed algorithms are embedded into…	D. Schörkhuber	Details
Evaluation of a 3D Reconstruction System Comprising Multiple Stereo Cameras Recent advances in the fields of media production and mixed/virtual reality have generated an increasing demand for high-quality 3D models obtained…	C. Kapeller	Details
Interactive Post-Processing of 2D-Plus-Depth Videos: Algorithms, Implementation and Evaluation One of the approaches to reconstruct the depth of real-world objects or scenes consists of using stereo cameras to record them in image or video…	B. Sespede	Details
Robot-Assisted Game Incorporating Emotional Postures for Children with ASD Joint attention has been shown to have an important impact on the development of the social cognition in children. Children with autism spectrum…	D. Stoeva	Details
Real-Time Visualization Pipeline for Dynamic Point Cloud Data Current developments in sensor and computer vision technologies are pushing the boundaries of extended reality (XR) applications. Digital…	H. Hofer	Details
Performance Analysis of a Stereo Matching Implementation in OpenCL Stereo matching is one of the first steps in the process of calculating 3D information from two 2D images. To triangulate a 3D point from two…	S. Rotheneder	Details

Intelligent Film Assistant for Personalized Video Creation on Mobile Devices We describe the development of an intelligent film assistant system that supports the creation of professional video content on mobile devices such…	D. Schörkhuber, F. Seitner, B. Salzbrunn, M. Gelautz, G. Braun	Details
Improved Cooperative Stereo Matching for Dynamic Vision Sensors with Ground Truth Evaluation Event-based vision, as realized by bio-inspired Dynamic Vision Sensors (DVS), is gaining more and more popularity due to its advantages of high…	E. Piatkowska, J. Kogler, A. Belbachir, M. Gelautz	Details
Depth-guided Disocclusion Inpainting for Novel View Synthesis The generation of novel views is a crucial processing step in 3D content generation, since it gives control over the amount of depth impression on…	T. Rittler, M. Nezveda, F. Seitner, M. Gelautz	Details
Digital Playbook - A Teaching Tool for American Football A playbook in American Football can consist of hundreds of plays, and to learn each play and the corresponding assignments and responsibilities is a…	M. Vorstandlechner, M. Gelautz, C. Putz	Details
Stereo reconstruction of sports scenes: algorithms, applications and challenges M. Gelautz, F. Seitner, C. Kapeller, N. Brosch: "Stereo reconstruction of sports scenes: algorithms, applications and challenges"; in: "International…	M. Gelautz, F. Seitner, C. Kapeller, N. Brosch	Details

Algorithms for 3D film content generation and post-processing In this talk we present algorithms for 3D reconstruction and novel view synthesis that form part of a 3D film processing chain which aims at…	M. Gelautz, M. Nezveda, N. Brosch, F. Seitner	Details
3D Scene Reconstruction via Hierarchical Stereo Matching The reconstruction of 3D scenes from a pair of stereo images/videos that were captured from slightly displaced camera view points presents an…	M. Nezveda, M. Gelautz	Details
Towards Perceptually Coherent Depth Maps in 2D-to-3D Conversion We propose a semi-automatic 2D-to-3D conversion algorithm that is embedded in an efficient optimization framework, i.e., cost volume filtering, which…	N. Brosch, T. Schausberger, M. Gelautz	Details
Linear Optimization Approach for Depth Range Adaption of Stereoscopic Videos Depth-Image Based Rendering (DIBR) techniques enable the creation of virtual views from color and corresponding depth images. In stereoscopic 3D film…	W. Zellinger, B. Moser, A. Chouikhi, F. Seitner, M. Nezveda, M. Gelautz	Details

Spatio-temporal Video Analysis for Semi-automatic 2D-to-3D Conversion This thesis addresses the problem of cost-efficiently converting monoscopic (2D) videos to stereoscopic (3D) videos. Common practices to perform such…	N. Brosch	Details
Design and Evaluation of Stereo Matching Techniques for Silicon Retina Cameras Nowadays, techniques for 3D reconstruction that are used in a variety of computer vision applications need to account for the 3D structure of a…	J. Kogler	Details

Trifocal system for high-quality inter-camera mapping and virtual view synthesis We present an innovative L-shaped trifocal system involving a high-end main camera with a compact assistant stereo rig attached to it. The system can…	F. Seitner, M. Nezveda, M. Gelautz, G. Braun, C. Kapeller, W. Zellinger, B. Moser	Details
Structured-light-based Depth Reconstruction Using Low-light Pico Projector In this work we investigate an infrared structured light prototype which is intended for 3D reconstruction in resource-restricted mobile…	T. Rittler, F. Seitner, M. Gelautz	Details
Fast PatchMatch Stereo Matching using Multi-Scale Cost Fusion for Automotive Applications J. Cho, M. Humenberger: "Fast PatchMatch Stereo Matching using Multi-Scale Cost Fusion for Automotive Applications"; Talk: 2015 IEEE Intelligent…	J. Cho, M. Humenberger	Details

IRYSTEC - perceptual display engine T. Akhavan: "IRYSTEC - perceptual display engine"; Talk: 4 th Automotive Platform Meeting, DFF - The German Flat Panel Display Forum e.V .,…	T. Akhavan	Details
Coarse-to-fine stereo matching for high resolution images Stereo matching denotes the problem of finding correspondences in pairs of images in order to perform 3D reconstruction. However, high resolution…	M. Nezveda	Details

Geometrically Motivated Dense Large Displacement Matching in Continuous Label Spaces The problem of correspondence search (or matching) remains a central focus of research in a variety of domains of computer vision. To date, the…	M. Hornacek	Details
Dense Stereo Matching for Urban Outdoor Scenes Dense stereo matching is an active research topic in the area of Computer Vision. Depth information is extracted from a dense correspondence search…	K. Lasinger	Details
Temporally Coherent Cost Volume Filtering-based Depth Propagation in Videos The growing availability of three-dimensional (3D) displays in the commercial sector and related trends in this field increase the demand for 3D…	T. Schausberger	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
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
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
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

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

Secrets of Adaptive Support Weight Techniques for Local Stereo Matching In recent years, local stereo matching algorithms have again become very popular in the stereo community. This is mainly due to the introduction of…	A. Hosni, M. Bleyer, M. Gelautz	Details
Local Color Transfer between Images Using Dominant Colors A color-transfer method that can transfer colors of an image to another for the local regions using their dominant colors is proposed. In order to…	J. Yoo, M. Park, J. Cho, K. Lee	Details
Fast Cost-Volume Filtering for Visual Correspondence and Beyond Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions…	A. Hosni, C. Rhemann, M. Bleyer, C. Rother, M. Gelautz	Details

Dense RGB-D Correspondence Search at Large Displacement (talk) M. Hornacek: "Dense RGB-D Correspondence Search at Large Displacement (talk)"; Talk: Talk an der TU Dresden, Dresden, Deutschland; 12-20-2013.	M. Hornacek	Details
Image and Video Matting (ICCV 2013 Tutorial) Matting refers to the problem of accurate extraction of foreground objects in images and video, which plays a fundamental role in image and video…	E. Varnousfaderan, M. Gelautz, B. Price, J. Cho	Details
Depth Super Resolution by Rigid Body Self-Similarity in 3D (talk) M. Hornacek: "Depth Super Resolution by Rigid Body Self-Similarity in 3D (talk)"; Talk: VRVis Forum, Wien; 07-25-2013.	M. Hornacek	Details
Depth Super Resolution by Rigid Body Self-Similarity in 3D (talk) M. Hornacek: "Depth Super Resolution by Rigid Body Self-Similarity in 3D (talk)"; Talk: Wissenschaftlicher Vortrag am McGill University, Montreal,…	M. Hornacek	Details
Depth Super Resolution by Rigid Body Self-Similarity in 3D (talk) M. Hornacek: "Depth Super Resolution by Rigid Body Self-Similarity in 3D (talk)"; Talk: Wissenschaftlicher Vortrag am University College London,…	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: Annual Workshop of the Austrian Association for Pattern Recognition,…	M. Hornacek	Details
Recent Advances in Local Stereo Matching In this talk we address recent research in the field of local stereo matching, with a focus on adaptive support weight algorithms. In particular, we…	M. Gelautz	Details
3D Film/TV - Research and Challenges In this talk we address the topic of 3D scene reconstruction from stereo views in the context of 3D film/TV applications. After an introduction into…	M. Gelautz	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
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

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
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

Asynchronous Stereo Vision for Event-Driven Dynamic Stereo Sensor Using an Adaptive Cooperative Approach This paper presents an adaptive cooperative approach towards the 3D reconstruction tailored for a bio-inspired depth camera: the stereo dynamic…	E. Piatkowska, A. Belbachir, M. Gelautz	Details
Depth Map Inpainting and Super-Resolution based on Internal Statistics of Geometry and Appearance Depth maps captured by multiple sensors often suffer from poor resolution and missing pixels caused by low reflectivity and occlusions in the scene.…	S. Ikehata, J. Cho, K. Aizawa	Details
Ground Truth Evaluation for Event-Based Silicon Retina Stereo Data In this paper we present a new approach for the evaluation of event-based Silicon Retina stereo matching results. The evaluation of stereo matching…	J. Kogler, F. Eibensteiner, M. Humenberger, M. Gelautz, J. Scharinger	Details
Depth Super Resolution by Rigid Body Self-Similarity in 3D We tackle the problem of jointly increasing the spatial resolution and apparent measurement accuracy of an input low-resolution, noisy, and perhaps…	M. Hornacek, C. Rhemann, M. Gelautz, C. Rother	Details
Depth Map Upsampling using Cost-Volume Filtering Depth maps captured by active sensors (e.g., ToF cameras and Kinect) typically suffer from poor spatial resolution, considerable amount of noise, and…	J. Cho, S. Ikehata, H. Yoo, M. Gelautz, K. Aizawa	Details
A framework for HDR stereo matching using multi-exposed images Real world scenes that contain high dynamic range illumination present a special challenge for stereo matching algorithms due to a lack of texture in…	T. Akhavan, H. Yoo, M. Gelautz	Details

Support Framework for Obstacle Detection on Autonomous Trains Autonomous driving vehicles are a rapidly emerging technlogy that will radically transform the face of public and personal transportation in the near…	M. Gschwandtner	Details
Tracking and Visual Quality Inspection in Harsh Environments M. Heber: "Tracking and Visual Quality Inspection in Harsh Environments"; Supervisor, Reviewer: H. Bischof, M. Gelautz; Institute for Computer…	M. Heber	Details
Stereo Matching M. Bleyer: "Stereo Matching"; Institut für Softwaretechnik und interaktive Systeme, 2013.	M. Bleyer	Details
Virtual HW/SW Prototyping for Design and Runtime Prediction of Parallel Video Coding Systems The high computational demands of state-of-the-art video coding standards such as H.264 pose serious challenges on embedded processor architectures.…	F. Seitner	Details
Novel Methods for Discontinuity Preserving Support Aggregation in Local Stereo Matching This thesis addresses the stereo matching problem, in which the depth information for scene objects is obtained by matching corresponding pixels in a…	A. Hosni	Details

Extracting 3D Scene-consistent Object Proposals and Depth from Stereo Images This work combines two active areas of research in computer vision: unsupervised object extraction from a single image, and depth estimation from a…	M. Bleyer, C. Rhemann, C. Rother	Details
Accuracy-Efficiency Evaluation of Adaptive Support Weight Techniques For Local Stereo Matching Adaptive support weight (ASW) strategies in local stereo matching have recently attracted many researchers due to their compelling results. In this…	A. Hosni, M. Gelautz, M. Bleyer	Details
Spatio-temporally Coherent Interactive Video Object Segmentation via Efficient Filtering In this paper we propose a fast, interactive object segmentation and matting framework for videos that allows users to extract objects from a video…	N. Brosch, A. Hosni, C. Rhemann, M. Gelautz	Details
Spatiotemporal Multiple Persons Tracking Using Dynamic Vision Sensor Although motion analysis has been extensively investigated in the literature and a wide variety of tracking algorithms have been proposed, the…	E. Piatkowska, A. Belbachir, S. Schraml, M. Gelautz	Details
Quality Analysis of Virtual Views on Stereoscopic Video Content Depth Image-Based Rendering (DIBR) allows the creation of virtual camera viewpoints from a 2D image and its corresponding disparity map. This enables…	M. Eisenbarth, F. Seitner, M. Gelautz	Details
Motion Segmentation in Videos from Time of Flight Cameras This paper investigates motion estimation and segmentation of independently moving objects in video sequences from a range camera. Specifically, we…	S. Ghuffar, N. Brosch, N. Pfeifer, M. Gelautz	Details

3D Film - Herausforderungen an die Wissenschaft M. Gelautz: "3D Film - Herausforderungen an die Wissenschaft"; Talk: Informatiktag 2012, Wien (invited); 11-05-2012.	M. Gelautz	Details
Interactive Video Segmentation via Efficient Filtering In [2], we present a fast, interactive segmentation and matting framework for videos. It is based on recent work [5] that recovers high-quality…	N. Brosch, A. Hosni, C. Rhemann, M. Gelautz	Details
Ausgewählte Kapitel aus Visual Computing: 3D Video und Bildstilisierung M. Gelautz: "Ausgewählte Kapitel aus Visual Computing: 3D Video und Bildstilisierung"; Talk: Gastvortrag FH Kapfenberg, Kapfenberg (invited);…	M. Gelautz	Details

Zeitlich konsistente Disparitätsbestimmung in einem globalen Stereo Matching Verfahren The increasingly popular 3D technology extends the movie experience by an additional dimension: depth. However, this technology introduces entirely…	E. Hiller	Details
Evaluierung eines nichtlinearen Disparitätsmapping Ansatzes zur Anpassung von Stereo 3D Inhalten When producing a high quality 3D film via stereo cameras, producers often have to face the challenge to make changes of the depth perception in post…	S. Stransky	Details
Integration von automatischer Shoterkennung und Disparitätsabschätzung in ein Stereo Matching Framework Two 2D-images, recorded from a pair of parallel cameras, have a slightly different perspective because of their horizontal displacement. This can be…	V. Nake	Details
Eine Untersuchung zur Wichtigkeit von Farbe in Stereo-Matching The aim of stereo-algorithms is to find corresponding points in two horizontally displaced images. The displacement between these corresponding…	A. Hasslacher	Details

Content generation for 3D video/TV A lack of suitable 3D content currently constitutes a major bottleneck for transferring the recent success of 3D cinema to our home TV. In this paper…	N. Brosch, A. Hosni, G. Ramachandran, L. He, M. Gelautz	Details
Evaluation of data-parallel H.264 decoding approaches for strongly resource-restricted architectures Decoding of an H.264 video stream is a computationally demanding multimedia application which poses serious challenges on current processor…	F. Seitner, M. Bleyer, M. Gelautz, R. Beuschel	Details

Temporally Consistent Disparity and Optical Flow via Efficient Spatio-temporal Filtering This paper presents a new efficient algorithm for computing temporally consistent disparity maps from video footage. Our method is motivated by…	A. Hosni, C. Rhemann, M. Bleyer, M. Gelautz	Details
PatchMatch Stereo - Stereo Matching with Slanted Support Windows Common local stereo methods match support windows at integer-valued disparities. The implicit assumption that pixels within the support region have…	M. Bleyer, C. Rhemann, C. Rother	Details
Real-time Local Stereo Matching Using Guided Image Filtering Adaptive support weight algorithms represent the state-of-the-art in local stereo matching. Their limitation is a high computational demand, which…	A. Hosni, M. Bleyer, C. Rhemann, M. Gelautz, C. Rother	Details
A Global Sampling Method for Alpha Matting Alpha matting refers to the problem of softly extracting the foreground from an image. Given a trimap (specifying known foreground/background and…	K. He, C. Rhemann, C. Rother, X. Tang, J. Sun	Details
Fast Cost-Volume Filtering for Visual Correspondence and Beyond Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions…	C. Rhemann, A. Hosni, M. Bleyer, C. Rother, M. Gelautz	Details
Object Stereo - Joint Stereo Matching and Object Segmentation This paper presents a method for joint stereo matching and object segmentation. In our approach a 3D scene is represented as a collection of visually…	M. Bleyer, C. Rother, P. Kohli, D. Scharstein, S. Sinha	Details
Object Removal by Depth-guided Inpainting Object removal by image inpainting aims at the visual uniformity of the inpainted blanks among their surroundings. Most inpainting algorithms pursue…	L. He, M. Bleyer, M. Gelautz	Details
Segmentation-Based Depth Propagation in Videos In this paper we propose a simple yet effective approach to convert existing 2D video content into 3D. We present a new semi-automatic algorithm that…	N. Brosch, C. Rhemann, M. Gelautz	Details
Temporally Consistent Disparity and Optical Flow via Efficient Spatio-temporal Filtering Abstract. This paper presents a new efficient algorithm for computing temporally consistent disparity maps from video footage. Our method is…	A. Hosni, C. Rhemann, M. Bleyer, M. Gelautz	Details

Recent Progress in Stereo Matching M. Bleyer: "Recent Progress in Stereo Matching"; Talk: The 29th Pattern Recognition and Computer Vision Colloquium - Czech Technical University, Prag…	M. Bleyer	Details
Ausgewählte Kapitel aus Visual Computing: 3D Video und Bildstilisierung M. Gelautz: "Ausgewählte Kapitel aus Visual Computing: 3D Video und Bildstilisierung"; Talk: Gastvortrag FH Kapfenberg, Kapfenberg (invited);…	M. Gelautz	Details
Recent advances in segmentation and stereo matching C. Rhemann: "Recent advances in segmentation and stereo matching"; Talk: Eingeladener Vortrag am Max Planck Inst., MPI Saarbrücken, Deutschland…	C. Rhemann	Details
Recent Progress in Stereo Matching M. Bleyer: "Recent Progress in Stereo Matching"; Talk: ÖAGM / AAPR Workshop 2011, Graz (invited); 03-26-2011 - 03-27-2011.	M. Bleyer	Details

2019

Conferences

Talks

Theses

2018

Books

Conferences

Reports

Talks

Theses

2017

Conferences

2016

Journals

Conferences

Reports

Talks

Theses

2015

Conferences

Talks

Theses

2014

Books

Journals

Conferences

Talks

Theses

2013

Journals

Conferences

Talks

Theses

2012

Journals

Conferences

Talks

Theses

2011

Journals

Conferences

Talks

Theses

2010

Journals

Conferences

Talks

Theses

2009

Journals

Conferences

Reports

Talks

Theses

2008

Conferences

Talks

Theses

2007

Journals

Conferences

Talks

Theses

2006

Conferences

Reports

Talks

Theses

2005

Journals

Conferences

Talks

Theses

2004

Books

Journals

Talks

2003

Books

Journals

Bestimmung von Hominoidsegmenten aus 3D-Bodyscannerdaten K. Schiffl: "Bestimmung von Hominoidsegmenten aus 3D-Bodyscannerdaten"; Supervisor: M. Gelautz, A. Baca; Institute of Software Technology and…	K. Schiffl	Details
Evaluierung von Algorithmen zur Novel-View-Generierung aus Stereobildern M. Eisenbarth: "Evaluierung von Algorithmen zur Novel-View-Generierung aus Stereobildern"; Supervisor: M. Gelautz, F. Seitner; Institute of Software…	M. Eisenbarth	Details
Rauschunterdrückung einer nicht ausgerichteten Bildfolge R. Kloibhofer: "Rauschunterdrückung einer nicht ausgerichteten Bildfolge"; Supervisor: M. Gelautz, C. Rhemann; 188/2, 2011.	R. Kloibhofer	Details
Erstellung eines Datensatzes zur Evaluierung von Stereo-Matching-Algorithmen B. Gneiss: "Erstellung eines Datensatzes zur Evaluierung von Stereo-Matching-Algorithmen"; Supervisor: M. Gelautz, C. Rhemann; 188/2, 2011.	B. Gneiss	Details
Die Bedeutung von Alpha-Matting für die Darstellung von Bildern auf 3D-Bildschirmen: eine Benutzerstudie S. Arnberger: "Die Bedeutung von Alpha-Matting für die Darstellung von Bildern auf 3D-Bildschirmen: eine Benutzerstudie"; Supervisor: M. Gelautz, C.…	S. Arnberger	Details
Interactive image segmentation in higher order graphs D. Antensteiner: "Interactive image segmentation in higher order graphs"; Supervisor: M. Gelautz, C. Rhemann; 188/2, 2011.	D. Antensteiner	Details
Echtzeitansätze in der Stereoanalyse C. Czermak: "Echtzeitansätze in der Stereoanalyse"; Supervisor: M. Bleyer, M. Gelautz; Institute of Software Technology and Interactive Systems, 2011.	C. Czermak	Details
Effiziente kantenerhaltende Glättung und ihre Anwendung in der Praxis G. Braun: "Effiziente kantenerhaltende Glättung und ihre Anwendung in der Praxis"; Supervisor: M. Bleyer, M. Gelautz; Institute of Software…	G. Braun	Details
Evaluierung und Entwurf von Epipolarrektifizierungsverfahren zur Verwendung in einem Stereovision Framework A. Bogner: "Evaluierung und Entwurf von Epipolarrektifizierungsverfahren zur Verwendung in einem Stereovision Framework"; Supervisor: M. Bleyer, C.…	A. Bogner	Details
Real-Time Stereo Matching for Embedded Systems in Robotic Applications C. Humenberger: "Real-Time Stereo Matching for Embedded Systems in Robotic Applications"; Supervisor, Reviewer: M. Vincze, M. Gelautz; E376, 2011;…	M. Humenberger	Details

Learning an Interactive Segmentation System Many successful applications of computer vision to image or video manipulation are interactive by nature. However, parameters of such systems are…	H. Nickisch, C. Rother, P. Kohli, C. Rhemann	Details
Surface Stereo with Soft Segmentation This paper proposes a new stereo model which encodes the simple assumption that the scene is composed of a few, smooth surfaces. A key feature of our…	M. Bleyer, C. Rother, P. Kohli	Details
A Spatially Varying PSF-based Prior for Alpha Matting In this paper we considerably improve on a state-of-the-art alpha matting approach by incorporating a new prior which is based on the image formation…	C. Rhemann, C. Rother, P. Kohli, M. Gelautz	Details
Near Real-Time Stereo With Adaptive Support Weight Approaches Algorithms based on the adaptive support weight strategy currently represent the state-of-the-art in local stereo matching. Unfortunately, their…	A. Hosni, M. Bleyer, M. Gelautz	Details
Does Color Really Help in Dense Stereo Matching? This paper investigates the role of color in global stereo matching approaches. In our evaluation study, we build various energy functions by…	M. Bleyer, S. Chambon	Details
Geodesic Adaptive Support Weight Approach For Local Stereo Matching Local stereo matching has recently experienced large progress by the introduction of new support aggregation schemes. These approaches estimate a…	A. Hosni, M. Bleyer, M. Gelautz, C. Rhemann	Details

Improving the Energy Model of Stereo Matching Algorithms Global stereo approaches formulate the stereo matching problem in terms of an energy function that is subject to optimization. It is known that…	M. Bleyer	Details
Filtering for Visual Correspondance C. Rhemann, A. Hosni, M. Bleyer, C. Rother, M. Gelautz: "Filtering for Visual Correspondance"; Talk: Microsoft Research Cambridge, Vision Meeting,…	C. Rhemann, A. Hosni, M. Bleyer, C. Rother, M. Gelautz	Details
Digitale Bildverarbeitung: Software-Werkzeuge für 3D-Video M. Gelautz: "Digitale Bildverarbeitung: Software-Werkzeuge für 3D-Video"; Talk: Innovationstag der Wirtschaftskammer Wien, Wien (invited); 12-09-2010.	M. Gelautz	Details
Digital Media - Visual Computing M. Gelautz: "Digital Media - Visual Computing"; Talk: femIT Ringvorlesung, Linz (invited); 11-04-2010.	M. Gelautz	Details
Spatial Scene Reconstruction for 3D Video/TV M. Gelautz, A. Hosni, M. Bleyer, C. Rhemann, C. Rother: "Spatial Scene Reconstruction for 3D Video/TV"; Talk: AIECS 2010, Graz (invited); 08-30-2010…	M. Gelautz, A. Hosni, M. Bleyer, C. Rhemann, C. Rother	Details
3D ohne Brille - Die Zukunft des Fernsehens M. Gelautz, F. Seitner, M. Bleyer: "3D ohne Brille - Die Zukunft des Fernsehens"; Talk: Consumer Content Conference, Köln (invited); 08-17-2010.	M. Gelautz, F. Seitner, M. Bleyer	Details
Surface Stereo with Soft Segmentation (Poster presentation - ICVSS 2010) M. Bleyer, C. Rother, P. Kohli: "Surface Stereo with Soft Segmentation (Poster presentation - ICVSS 2010)"; Poster: International Computer Vision…	M. Bleyer, C. Rother, P. Kohli	Details
Surface Stereo with Soft Segmentation (Talk for best presentation award - ICVSS 2010) M. Bleyer, C. Rother, P. Kohli: "Surface Stereo with Soft Segmentation (Talk for best presentation award - ICVSS 2010)"; Talk: International Computer…	M. Bleyer, C. Rother, P. Kohli	Details
A Spatially Varying PSF-based Prior for Alpha Matting C. Rhemann, C. Rother, P. Kohli, M. Gelautz: "A Spatially Varying PSF-based Prior for Alpha Matting"; Poster: International Computer Vision Summer…	C. Rhemann, C. Rother, P. Kohli, M. Gelautz	Details
Visual Computing - 3D Szenen in Bild/Video M. Gelautz: "Visual Computing - 3D Szenen in Bild/Video"; Talk: Gastvortrag FH Kapfenberg, Kapfenberg (invited); 06-09-2010.	M. Gelautz	Details
Geodesic Support Weights For Local Stereo This paper presents a window-based method for solving the stereo matching problem. Our contribution is to introduce the concept of connectivity for…	A. Hosni, M. Bleyer, M. Gelautz	Details
Digital Media - Visual Computing M. Gelautz: "Digital Media - Visual Computing"; Talk: femIT Ringvorlesung, Krems (invited); 03-04-2010.	M. Gelautz	Details
3D Video - Challenges and State-of-the-art Techniques M. Gelautz: "3D Video - Challenges and State-of-the-art Techniques"; Talk: Intelligent Systems, Innsbruck (invited); 01-12-2010.	M. Gelautz	Details

Runtime-optimised Intra Coding Mode Selection for Real-time H.264/AVC Video Coding H. Jordan: "Runtime-optimised Intra Coding Mode Selection for Real-time H.264/AVC Video Coding"; Supervisor: M. Gelautz, F. Seitner, M. Bleyer;…	H. Jordan	Details
Ein relationales Framework zur Verwaltung von videobasierten Trajektorien L. Frey: "Ein relationales Framework zur Verwaltung von videobasierten Trajektorien"; Supervisor: M. Gelautz; E188, 2010.	L. Frey	Details
Neue Kameraperspektiven bei TV Sportübertragungen A. Regner: "Neue Kameraperspektiven bei TV Sportübertragungen"; Supervisor: M. Gelautz; E188, 2010.	A. Regner	Details
Erstellung eines Standarddatensatzes für die Evaluierung von Alpha Matting Algorithmen und Aufbereitung der Resultate für die Lehre "Image Matting" is the process of separating a foreground object from a background in digital images. In order to quantitatively compare the results…	J. Pucher	Details
Modeling Sources and Sinks in Crowded Scenes by Clustering Trajectory Points Obtained by Video-based Particle Advection Analysis of real surveillance video footage is very challenging - hence this thesis provides solutions to enhance the quality of trajectories of…	R. Planinc	Details
Interactive Image Matting Image matting aims to extract a foreground object from a single natural image by recovering the partial transparency and corresponding color of the…	C. Rhemann	Details

Local Stereo Matching Using Geodesic Support Weights Local stereo matching has recently experienced large progress by the introduction of new support aggregation schemes. These approaches estimate a…	A. Hosni, M. Bleyer, M. Gelautz, C. Rhemann	Details
Image Segmentation Via Iterative Geodesic Averaging We present a simple and fast method for performing unsupervised segmentation. Our method works by centering a square window on each pixel of the…	A. Hosni, M. Bleyer, M. Gelautz	Details
Temporally Consistent Disparity Maps from Uncalibrated Stereo Videos We address the problem of computing a sequence of dense disparity maps from two synchronized video streams recorded by slightly displaced cameras.…	M. Bleyer, M. Gelautz	Details
Runtime-Optimised Intra-4x4 Mode-Decision for H.264/AVC Video Encoding We describe a method that considerably improves the computational behaviour of H.264 Intra-only encoders. Such Intra-only encoders come to use in…	H. Jordan, F. Seitner, M. Bleyer, M. Gelautz	Details
A Stereo Approach that Handles the Matting Problem via Image Warping We propose an algorithm that simultaneously extracts disparities and alpha matting information given a stereo image pair. Our method divides the…	M. Bleyer, M. Gelautz, C. Rother, C. Rhemann	Details
A Perceptually Motivated Online Benchmark for Image Matting The availability of quantitative online benchmarks for low-level vision tasks such as stereo and optical flow has led to significant progress in the…	C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli, P. Rott	Details
New Appearance Models for Image Matting Image matting is the task of estimating a fore- and background layer from a single image. To solve this ill posed problem, an accurate modeling of…	D. Singaraju, C. Rother, C. Rhemann	Details
An Evaluation of Interactive Image Matting Techniques Supported by Eye-Tracking Recently, the quantitative evaluation of interactive single image matting techniques has become possible by the introduction of high-quality ground…	C. Rhemann, M. Gelautz, B. Foelsner	Details

Evaluierung konkurrierender Datenterme für das Stereokorrespondenzproblem At the moment, many stereo matching algorithms (global and local) only use intensity values for the disparity map calculation. However, recent…	R. Gross	Details
Stereoscopic Non-Photorealistic Rendering E. Stavrakis: "Stereoscopic Non-Photorealistic Rendering"; Supervisor, Reviewer: M. Gelautz, E. Gröller; Institut für Softwaretechnik und Interaktive…	E. Stavrakis	Details

Evaluation of data-parallel splitting approaches for H.264 decoding The high computational demands of the H.264 decoding process pose serious challenges on current processor architectures. A natural way to tackle this…	F. Seitner, M. Bleyer, R. Schreier, M. Gelautz	Details
Development of Multi-Core Video Decoding Platforms based on High-Level Architecture Simulations The high computational demands of state-of-the-art video coding standards such as H.264 pose serious challenges on strongly resource-restricted…	F. Seitner, M. Bleyer, M. Gelautz	Details
Design Methodology for the SVENm Multimedia Engine The high computational demands of modern multimedia applications such as the H.264 video coding standard pose serious challenges on current hardware…	F. Seitner, J. Meser, G. Schedelberger, A. Wasserbauer, M. Bleyer, M. Gelautz, M. Schutti, R. Schreier, P. Vaclavik, G. Krottendorfer, G. Truhlar, T. Bauernfeind, P. Beham	Details
3D Scene Reconstruction by Stereo Methods for Analysis and Visualization of Sports Scenes M. Gelautz, M. Bleyer, D. Markovic, C. Rhemann: "3D Scene Reconstruction by Stereo Methods for Analysis and Visualization of Sports Scenes"; Talk:…	M. Gelautz, M. Bleyer, D. Markovic, C. Rhemann	Details
Improving Color Modeling for Alpha Matting This paper addresses the problem of extracting an alpha matte from a single photograph given a user-defined trimap. A crucial part of this task is…	C. Rhemann, C. Rother, M. Gelautz	Details
A Psychophysical Study of Fixation Behavior in a Computer Game Prediction of gaze behavior in gaming environments can be a tremendously useful asset to game designers, enabling them to improve gameplay,…	V. Sundstedt, E. Stavrakis, M. Wimmer, E. Reinhard	Details
Evaluation of Different Methods for Using Colour Information in Global Stereo Matching Approaches Global algorithms currently represent the state-of-the-art in dense stereo matching. These methods first set up an energy function. The energy…	M. Bleyer, S. Chambon, U. Poppe, M. Gelautz	Details
High Resolution Matting via Interactive Trimap Segmentation We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha…	C. Rhemann, C. Rother, A. Rav-Acha, T. Sharp	Details
A high-level simulator for the H.264/AVC decoding process in multi-core systems H.264 as a new-generation video coding algorithm is becoming increasingly important for international broadcasting standards such as DVB-H and DMB.…	F. Seitner, R. Schreier, M. Bleyer, M. Gelautz	Details
Simple but Effective Tree Structures for Dynamic Programming-based Stereo Matching This work describes a fast method for computing dense stereo correspondences that is capable of generating results close to the state-of-the-art. We…	M. Bleyer, M. Gelautz	Details
Interactive Tools for Image-based Stereoscopic Artwork E. Stavrakis, M. Gelautz: "Interactive Tools for Image-based Stereoscopic Artwork"; Poster: SPIE IS&T Electronic Imaging Conference, San Jose,…	E. Stavrakis, M. Gelautz	Details

Evaluierung von Fehlermetriken für Image Matting Image Matting aims to separate a foreground object from an arbitrary image, which is explained as a combination of foreground and background. The…	P. Rott	Details
Evaluation and Implementation of Improved Edge Detection Methods for an Industrial Robot Sewing Process A. Schöffmann: "Evaluation and Implementation of Improved Edge Detection Methods for an Industrial Robot Sewing Process"; Supervisor: M. Gelautz, M.…	A. Schöffmann	Details
Bildsegmentierung - eine Benutzerstudie unter Verwendung von Eye-tracking B. Foelsner: "Bildsegmentierung - eine Benutzerstudie unter Verwendung von Eye-tracking"; Supervisor: M. Gelautz, C. Rhemann; E 188, 2008.	B. Foelsner	Details

Experimental Combination of Intensity and Stereo Edges for Improved Snake Segmentation In this paper, we present an algorithm to combine edge information from stereo-derived disparitymaps with edges from the original intensity/color…	D. Markovic, M. Gelautz	Details
Graph-cut-based Stereo Matching using Image Segmentation with Symmetrical Treatment of Occlusions This paper describes a dense stereo matching algorithm for epipolar rectified images. The method applies colour segmentation on the reference image.…	M. Bleyer, M. Gelautz	Details

Final Internship talk at Microsoft Research Cambridge Presentation of current research results in the field of interactive image segmentation and matting.	C. Rhemann	Details
Mid-Internship talk at Microsoft Research Cambridge Presentation of current research results in the field of interactive image segmentation and matting.	C. Rhemann	Details
Image Matting Presentation of recent research results in the field of image segmentation and matting.	C. Rhemann	Details
An Introduction to media research at the IMS C. Rhemann: "An Introduction to media research at the IMS"; Talk: Wintergraph 2007, Nassfeld - Italien; 03-18-2007 - 03-20-2007.	C. Rhemann	Details