جستجوی استاد راهنمای دانشگاهی

Marc Pollefeysمشاهده پروفایل

استاد

• 3D Computer Vision
• Robotics
• Machine Learning
• +۵ مورد دیگر

Marc Pollefeys is a Full Professor of Computer Science at ETH Zurich and Director of the Microsoft Mixed Reality and AI Zurich Lab. He has held roles such as Visiting Professor at Stanford University (2007) and Assistant/Associate Professor at UNC-Chapel Hill (2002–2009). His research focuses on 3D computer vision, robotics, machine learning, and augmented reality. Education: PhD in Computer Science from KU Leuven (1999), followed by postdoctoral research there until 2002. He transitioned to academic roles at UNC-Chapel Hill before joining ETH Zurich in 2007. Research interests include 3D reconstruction, visual localization, SLAM, and applications in archaeology, urban modeling, and robotics. Notable projects include real-time 3D scanning, city-scale reconstruction, and autonomous vision-based drones. Key awards include ACM Fellow (2022), IEEE Fellow (2012), and ERC Starting Grant (2008). He advises numerous PhD students and collaborates with institutions like Google and Microsoft. Labs and teams: Leads the Computer Vision and Geometry (CVG) lab at ETH Zurich and directs the Microsoft Mixed Reality and AI Lab. His work bridges academia and industry, focusing on perception for mixed reality and autonomous systems.

Hans-Peter Seidelمشاهده پروفایل

استاد

• Computer Graphics
• 3D Image Analysis
• Digital Geometry Processing
• +۳ مورد دیگر

Hans-Peter Seidel is a leading academic in computer graphics, serving as Director of the Max Planck Institute for Informatics and Full Professor at Saarland University since 1999. Previously held roles include Full Professor at University of Erlangen (1992–1999) and Assistant Professor at University of Waterloo (1989–1992). Holds a PhD in Mathematics (1987) and Habilitation in Informatics (1989) from University of Tübingen. Research focuses on 3D image analysis, digital geometry processing, visual computing, and free viewpoint rendering. Key achievements include pioneering work in surface editing, motion capture, and multi-view video processing. Has organized major conferences like Eurographics and SIGGRAPH, serving as editor for journals including IEEE TVCG and Computer Aided Geometric Design. Recipient of the Eurographics Distinguished Career Award (2012), Gottfried Wilhelm Leibniz Prize (2003), and numerous fellowships. Led initiatives such as the Cluster of Excellence on Multimodal Computing and Interaction (M2CI) and the Max Planck Center for Visual Computing and Communication (MPC-VCC). Active in academic leadership roles including Eurographics Chair and DFG committees. Publications span over 30 SIGGRAPH and 50 Eurographics contributions, with an h-index of 62 and 14,000+ citations. Recognized as a top-cited researcher in computer graphics. Current research explores advanced visualization techniques and geometric modeling innovations.

Markus Steinbergerمشاهده پروفایل

دانشیار

• GPU Computing
• Parallel Algorithms
• Real-Time Rendering
• +۵ مورد دیگر

Markus Steinberger is an Associate Professor at Graz University of Technology (TU Graz), leading the GPU Computing and Visualization Group at the Institute for Computer Graphics and Vision. He holds a PhD (2013) and Habilitation (2020) in Computer Science from TU Graz. His research focuses on GPU scheduling, parallel computing, real-time rendering, and procedural content generation. He has held roles including Assistant Professor (2015–2021) and Director of Cloud Rendering at Huawei (2021–present). Education: MSc (2010), PhD (2013), Habilitation (2020) in Computer Science from TU Graz PostDoc and Research Positions: NVIDIA (2013–2014), Max Planck Institute (2015–2017) Research interests include dynamic resource scheduling, GPU algorithms, and high-performance visualization. His work has been recognized with awards such as the GI Dissertation Prize (2014), Eurographics Best Paper (2021), and the Heinz Zemanek Prize. Key Projects: Cloud-native rendering, procedural planet rendering, and GPU-optimized algorithms Advising includes PhD student Karl Haubenwallner. His lab explores cutting-edge techniques in real-time graphics and parallel computing.

Chen Chang-Wenمشاهده پروفایل

استاد

• Multimedia Signal Processing
• Multimedia Systems
• Image/Video Processing
• +۱ مورد دیگر

Chen Chang-Wen is a Chair Professor of Visual Computing at The Hong Kong Polytechnic University (2021–present). Previously, he was Empire Innovation Professor at the University at Buffalo (2008–2021) and held leadership roles including Dean of the School of Science and Engineering at CUHK Shenzhen (2017–2020). His research focuses on multimedia systems, signal processing, and communication. He is a Fellow of IEEE and SPIE, and has received numerous awards including the Alexander von Humboldt Research Award (2010) and the SUNY Chancellor's Award (2016). Chen has authored over 420 publications and holds three US patents. His work emphasizes interdisciplinary applications in visual computing, including contributions to autonomous systems, edge networks, and video quality assessment. He currently serves as Editor-in-Chief of IEEE Transactions on Systems, Man, and Cybernetics: Systems and leads initiatives in global university rankings and accreditation for engineering programs.

• Computer Vision
• Medical Informatics
• 3D Scene Understanding
• +۵ مورد دیگر

Overview Pedro Hermosilla Casajus is an Assistant Professor at the Department of Computer Vision within the Faculty of Informatics at Technische Universität Wien (TU Wien). His research focuses on advanced computer vision techniques with applications in medical imaging, 3D scene understanding, and deep learning methodologies. He is actively involved in teaching multiple courses including Fundamentals of Computer Vision, Deep Learning for Visual Computing, and Scientific Research and Writing. Projects & Collaborations MyeFLOW (2020–2025) : Developing automated analysis systems for flow cytometry data. EVOCATION (2018–2022) : Real-time shape acquisition technologies. Modeling the World at Scale (2020–2026) : Large-scale 3D modeling techniques. Research Highlights His work bridges computer vision with medical diagnostics, particularly in measurable residual disease detection using flow cytometry. He explores geometric deep learning for 3D point cloud analysis and scene graph generation, advancing unsupervised semantic segmentation methods. Recent contributions include stylized Gaussian splatting for neural rendering and open-vocabulary 3D scene understanding frameworks. Teaching He teaches core courses like Fundamentals of Computer Vision and supervises student projects in medical informatics, visual computing, and human-centered computing.

Horst Bischofمشاهده پروفایل

دانشیار

• Computer Vision
• Medical Imaging
• Pattern Recognition
• +۳ مورد دیگر

Ao.Univ.Prof. Dipl.-Ing. Dr.techn. Horst Bischof is an Associate Professor at Vienna University of Technology (TU Wien). His work focuses on computer vision, medical imaging, and pattern recognition. He has contributed to projects in automated medical diagnosis (e.g., rheumatoid arthritis assessment), 3D reconstruction, and cultural heritage preservation through advanced segmentation techniques. He has supervised numerous students including S. Veigl, A. Belbachir, and G. Langs. Bischof has edited proceedings like the 2005 Computer Vision Winter Workshop and published extensively on topics like Markov Random Fields, Active Appearance Models, and Canonical Correlation Analysis. His research bridges computer science and biomedical applications, with notable contributions to anatomical structure localization and robust model learning. He collaborates with institutions like the European Society of Musculoskeletal Radiology and has developed systems such as the RheumaCoachCAD for automated scoring of bone erosions. Education: Dipl.-Ing. (Master of Engineering) and Dr.techn. (Doctor of Technical Sciences) from TU Wien. Key Projects: CAD systems for rheumatoid arthritis, 3D rock-art segmentation, and MRF-based medical image analysis. Research interests emphasize integrating computational methods into clinical diagnostics and heritage conservation. His work on sparse MRF models and group-wise learning has advanced automated medical image processing techniques.

David Schinaglمشاهده پروفایل

پژوهشگر

• Computer Vision
• Autonomous Driving
• 3D Object Detection
• +۳ مورد دیگر

David Schinagl is affiliated with the Institute of Visual Computing at TU Graz. His research focuses on LiDAR-based 3D object detection , explainable AI , and autonomous driving technologies . He has contributed to methods like OccAM's Laser for model interpretability and MAELi for large-scale LiDAR processing. His work emphasizes sensor data analysis and geometric confidence enhancement. Publications span top venues including CVPR, ICCV, and WACV (2018–2024). His GitHub repository demonstrates implementations like the OccAM's Laser demo for LiDAR attribution maps.

Emmanuel Iarussiمشاهده پروفایل

استادیار

• AI
• Computer Graphics
• Medical Imaging
• +۲ مورد دیگر

Emmanuel Iarussi is an Assistant Professor at the Universidad Torcuato Di Tella and a researcher at CONICET in Buenos Aires. He holds a Ph.D. in Computer Graphics from INRIA Sophia Antipolis, supervised by Adrien Bousseau and George Drettakis, and completed a postdoc at IST Austria under Bernd Bickel. His engineering degree is from UNICEN University (2012). His research bridges AI, computer graphics, and medical imaging, focusing on generative models for 2D/3D content manipulation. Research Interests: His work spans AI-driven medical imaging, generative models for vascular structures, ultrasound simulation, and bone microstructure modeling. Key areas include autoregressive modeling, variational autoencoders, and applications in healthcare and biomedical engineering. Recent Trends in Articles: Recent publications emphasize combining AI techniques with medical applications, such as vascular geometry synthesis, melanoma detection reviews, and ultrasound realism enhancement. His work often intersects generative networks and clinical diagnostics. Grants & Recognition: Awarded a $69,960 grant from the Sloan Foundation’s Trust in AI initiative (2024). Active in workshops on AI ethics, public discourse, and open science. Labs & Teams: Leads projects like VisDecode (AI-driven scientific plot analysis) and contributes to repositories like generative3DSpongiosa for bone microstructure modeling.

Beatrix C. Hiesmayrمشاهده پروفایل

دانشیار

• Quantum Information Theory
• Entanglement Characterisation & Witnesses
• High-Energy Discrete-Symmetry Tests
• +۴ مورد دیگر

Beatrix C. Hiesmayr is a Privatdozent (habilitated Associate Professor) of theoretical physics at the University of Vienna, Faculty of Physics, where she has led the Quantum Particle Workgroup since 2008. She serves as elected member of the works-council for scientific staff and teaches a broad spectrum of courses from introductory lab sessions to advanced quantum-information theory. Education & qualifications: The text does not list prior degrees, but her title Mag. Dr. and the rank Privatdoz. indicate a doctorate and post-doctoral habilitation at an Austrian university. Research interests sit at the tripartite interface of quantum information science , high-energy particle theory and medical-imaging technology . Her group develops mathematical tools to detect and quantify entanglement in composite qudit systems, subjects discrete space-time symmetries to precision tests with positronium decays, and translates the resulting detector know-how into the world-first plastic-scintillator total-body PET scanner (J-PET). Across 15 representative papers (2023-2025) she explores entanglement witnesses, distillation protocols, quantum neural networks, and realistic PET engineering, signalling a coherent programme that moves from abstract quantum-structure theorems to hardware prototypes now entering clinical feasibility studies. Although no specific grants or honours are mentioned, she currently coordinates the COST action “Relativistic Quantum Information” (CA21106) and her group operates an international consortium on J-PET development. Student names are not disclosed in the supplied text. Contact: beatrix.hiesmayr@univie.ac.at — Boltzmanngasse 5, 1090 Wien, room 503.

• Computer Vision
• Autonomous Driving
• 3D Reconstruction
• +۵ مورد دیگر

Ao.Univ.Prof. Margrit Gelautz is an Associate Professor at TU Wien's Computer Vision research department (E193-01), affiliated with the Institute for Software Technology and Interactive Systems (E188). Her work focuses on computer vision applications in autonomous driving, robotics, and 3D reconstruction. She leads projects on driver monitoring systems, vulnerable road user detection, and human-robot interaction. Recent research includes 3D bounding box prediction, synthetic data-driven pose estimation, and real-time sensor systems. She advises over 20 graduate students and collaborates on automotive platforms integrating vision-based safety systems. Her contributions span sensor fusion, stereo matching algorithms, and interactive video tools. Key projects include multimodal sensor-lighting systems for traffic safety, 3D scene completion, and intelligent workflow design for low-cost 3D film production. Her work emphasizes practical applications like in-cabin monitoring systems and adaptive lighting control. She develops semi-automatic annotation tools for traffic datasets and explores nonverbal communication in human-robot interaction using platforms like Pepper humanoid robots.

Friedrich Fraundorferمشاهده پروفایل

استاد

• 3D Computer Vision
• Robot Vision
• Multi View Geometry
• +۴ مورد دیگر

Friedrich Fraundorfer is a Professor at Graz University of Technology, specializing in 3D Computer Vision and Autonomous Systems at the Institute of Computer Graphics and Vision (ICG). He has held academic positions at institutions including ETH Zurich, University of North Carolina at Chapel Hill, and Technische Universität München, where he served as Deputy Director of the Chair of Remote Sensing Technology. Research : Focuses on Micro Aerial Vehicle (MAV) autonomy, Visual-Inertial Fusion, and Multi-View Geometry. Projects : Led EU-funded SFly (autonomous MAVs for search-and-rescue), SNF MAV (camera-only 3D mapping), and VCharge (vision-based self-driving cars). Teaching : Offers courses like 'Camera Drones' and 'Mathematical Principles in Vision.' His Pixhawk project created open-source MAV platforms adopted globally. Key Collaborations : With NVIDIA, Volkswagen AG, University of Zurich, and German Space and Aerospace Center (DLR). His students (e.g., Dominik Hirner, Rafael Weilharter) have published on lightweight CNNs for stereo vision and self-supervised 3D reconstruction.

Linus Frankeمشاهده پروفایل

پژوهشگر

• Computer Graphics
• Perceptual Rendering
• Computer Vision
• +۳ مورد دیگر

Linus Franke is a postdoctoral researcher at Inria Sophia Antipolis in France, affiliated with the GraphDeco research group under George Drettakis. He previously completed his PhD at the Chair of Visual Computing , Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) in Germany under Marc Stamminger. His research focuses on Computer graphics Perceptual rendering Computer vision Machine learning Neural rendering Novel view synthesis Key trends in his recent publications include neural rendering , 3D Gaussian splatting , radiance fields , and real-time rendering with applications in virtual reality and light field displays. His work often integrates point clouds , differentiable rendering , and GPU optimization techniques. His personal website at lfranke.github.io highlights projects like VET (Visual Error Tomography) and TRIPS (Trilinear Point Splatting for Real-Time Rendering).