جستجوی استاد راهنمای دانشگاهی

Christian Theobaltمشاهده پروفایل

استاد

• Computer Science
• Artificial Intelligence
• Computer Vision
• +۵ مورد دیگر

Christian Theobalt is a Professor of Computer Science at Saarland University and Scientific Director of the Visual Computing and Artificial Intelligence Department at the Max Planck Institute for Informatics . He leads the Saarbruecken Center for Visual Computing as a strategic partnership between Google and MPI. PhD in Computer Science (2005) from MPI-INF/Saarland University Postdoctoral Researcher at MPI (2005-2007) Visiting Assistant Professor at Stanford (2007-2009) His research focuses on the intersection of Computer Graphics, Computer Vision, and Artificial Intelligence , with specializations in: 3D/4D Human Reconstruction Neural Rendering Performance Capture Geometric Deep Learning Volumetric Video Quantum Visual Computing Recent article trends show emphasis on: Quantum computing applications in visual reconstruction Neural rendering with radiance fields Human motion capture from egocentric views Gesture-language interaction modeling Multi-modal scene understanding Real-time free-viewpoint rendering Scientific Awards : Fellow of EUROGRAPHICS (2022) CVPR Best Student Paper Honorable Mention (2020) ERC Consolidator Grant (2017) Karl Heinz Beckurts Award (2017) Busy Beaver Teaching Award (2016) ERC Starting Grant (2013) Advising over 50 students and researchers including: Current researchers: Viktor Rudnev, Linjie Lyu, Mohit Mendiratta Postdocs: Kwang In Kim, Kiran Varanasi Alumni: Franziska Mueller (Google), Dushyant Mehta (Qualcomm), Ayush Tewari (MIT) Grants include ERC grants, Google Glass Research Award, and multiple industry partnerships. His lab maintains cutting-edge facilities with: Multi-camera capture systems Quantum annealing infrastructure HDR radiance field technology GPU clusters for AI research Time-of-flight imaging systems Event camera arrays

Stefan Leuteneggerمشاهده پروفایل

استادیار

• Mobile Robotics
• SLAM (Simultaneous Localization and Mapping)
• Computer Vision
• +۷ مورد دیگر

Prof. Stefan Leutenegger is a tenure-track Assistant Professor at Technische Universität München (TUM), leading the Machine Learning for Robotics group within the TUM School of Computation, Information, and Technology. Previously, he held roles as Senior Lecturer (2018–2021) and Lecturer (2014–2018) at Imperial College London's Dyson Robotics Lab, where he founded the Smart Robotics Lab. He earned his PhD (2014) from ETH Zurich, focusing on autonomous solar-powered aircraft navigation, and holds BSc (2006) and MSc (2009) in Mechanical Engineering from ETH Zurich. His research centers on mobile robotics, particularly enabling robots (e.g., drones) to perceive and navigate complex environments using machine learning and sensor data fusion. Key focus areas include SLAM, event-based vision, 3D reconstruction, and autonomous exploration. He has pioneered algorithms like BRISK (2011), OKVIS (2014), and ElasticFusion (2016), advancing real-time robotics perception. Notable Awards: Imperial College President's Award (2018), Best ECCV Paper (2016), ETH Medal for Dissertations (2015). Labs: TUM's Machine Learning for Robotics Group, Imperial's Smart Robotics Lab. Publications: Over 100 papers, including seminal works in CVPR, ECCV, and Robotics: Science and Systems. Current projects include DigiForests (forest inventory via robotics), aerial additive manufacturing, and object-centric semantic mapping. His work bridges theory and practice, with applications in autonomous drones, construction robotics, and human-robot interaction.

• Computer Vision
• Machine Learning
• Autonomous Driving
• +۴ مورد دیگر

Prof. Laura Leal-Taixé is a Professor at the Technical University of Munich (TUM) in the Department of Informatics, leading the Dynamic Vision and Learning group. She holds the Rudolf Mößbauer Tenure Track Assistant Professorship, promoted to W3 Associate Professorship in 2022. Her research focuses on computer vision and machine learning, particularly video analysis, multi-object tracking, and autonomous driving applications. Education: B.Sc./M.Sc. in Telecommunications Engineering (Technical University of Catalonia, UPC) Ph.D. in Information Processing (Leibniz University of Hannover, Germany) Postdoctoral Research at ETH Zürich (Switzerland) and TUM Research Interests: Laura’s work addresses challenges in video analysis, including motion analysis, semantic segmentation, and integrating social dynamics into urban traffic modeling. Her project socialMaps , funded by the Sofja Kovalevskaja Award, explores decoupling vehicle and pedestrian traffic using dynamic maps. Her research combines optimization techniques, deep learning, and sensor data for real-world applications like autonomous systems. Recent Trends: Her publications highlight advancements in multi-object tracking, 3D LiDAR segmentation, and trajectory forecasting, emphasizing neural networks and geometric approaches. Collaborations with industry and academia underscore her work’s practical impact. Awards: 2017 Sofja Kovalevskaja Award (€1.65M, Humboldt Foundation) 2017 DAAD Australia-German Joint Research Grant Travel grants from Women in CV, CVPR Doctoral Consortium, and Vodafone Foundation Labs & Projects: Leads the Dynamic Vision and Learning group at TUM, focusing on vision-based AI for autonomous systems and environmental monitoring. Active in developing datasets like DynamicEarthNet for semantic change analysis.

Benjamin Busamمشاهده پروفایل

پژوهشگر

• 3D Computer Vision
• Multi-Modal Sensor Fusion
• Collaborative Robotics
• +۶ مورد دیگر

Dr. Benjamin Busam is a Senior Research Scientist at the Technical University of Munich , affiliated with the Chair for Computer Science Applications in Medicine under Prof. Nassir Navab. Starting September 2025, he will hold the Professorship for Photogrammetry and Remote Sensing at TUM. His career includes leadership roles at FRAMOS Imaging Systems and Huawei Research in London. Education: Mathematics (TUM), Mathematics and Physics (ParisTech, University of Melbourne), PhD in Mathematics (TUM, 2014) His research focuses on 3D computer vision , multi-modal sensor fusion , and their applications in collaborative robotics and augmented reality . He specializes in projective geometry , 6D pose estimation , and neural radiance fields , with a particular emphasis on photometrically challenging environments. Recent publications highlight advancements in 3D scene understanding , neural rendering , and medical imaging , often leveraging machine learning and vision-language models . His work has been recognized through awards like the EMVA Young Professional Award (2015) and Innovation Pioneer of the Year (2019) , along with multiple Outstanding Reviewer distinctions at leading conferences. Dr. Busam has supervised numerous PhD and MSc students on topics including 6D pose estimation , medical augmented reality , and robotic ultrasound , collaborating with institutions like MIT , École Polytechnique , and University of Padova .

Yuanbo Xiangliمشاهده پروفایل

پژوهشگر

• 3D Computer Vision
• Deep Generative Modeling
• Photorealistic Scene Reconstruction
• +۳ مورد دیگر

Yuanbo Xiangli is a postdoctoral researcher at Cornell University , advised by Prof. Noah Snavely. Previously, he obtained his Ph.D. from the Multimedia Lab in the Department of Information Engineering at the Chinese University of Hong Kong (CUHK) , supervised by Prof. Dahua Lin. His research focuses on 3D computer vision and deep generative modeling for urban scene reconstruction. 3D scene reconstruction from sparse images Neural rendering and Gaussian splatting Deep generative modeling for urban environments Multi-source geospatial data processing City-scale modeling and synthetic datasets His recent work includes advanced NeRF extensions (BungeeNeRF, GridNeRF), Gaussian splatting enhancements (GSDF, Scaffold-GS), and urban scene datasets (MatrixCity, OmniCity). A pioneer in combining classical vision techniques with modern deep learning approaches. ICLR 2020 Spotlight Award Collaborates with leading researchers in photorealistic rendering, including Noah Snavely and Dahua Lin. Develops systems enabling efficient 3D reconstruction from diverse data sources like satellite imagery and street-level panoramas.

Hannes Taubenböckمشاهده پروفایل

استاد

• Remote Sensing
• Global Urbanization
• Urban Structure Analysis
• +۶ مورد دیگر

Prof. Dr. Hannes Taubenböck holds the Chair of Global Urbanization and Remote Sensing at the Julius-Maximilians University of Würzburg (Faculty of Philosophy, Institute of Geography and Geology) since 2022 and collaborates with the German Aerospace Center (DLR). His research bridges remote sensing with urban geography, focusing on: Global urbanization patterns and structural analysis Informal settlements (slums/refugee camps) Climate change and natural hazard vulnerability Migration dynamics via remote sensing and social media He obtained his PhD (2008) and habilitation (2019) at JMU Würzburg, preceded by geography studies at LMU Munich (1999-2004). His recent publications analyze: Climate impacts on African agriculture Urban permeability and walkability Border region disparities Heat exposure modeling Methodologically, he specializes in: Deep learning for earth observation Multi-modal data fusion Urban pattern classification Building stock analysis His work informs policy applications in: EU cohesion programs Disaster risk reduction Environmental justice Urban sustainability

• Biometrics
• Computer Vision
• Machine Learning
• +۴ مورد دیگر

Marina L. Gavrilova is a Professor at the University of Calgary, Canada. Her research focuses on biometric systems, computer vision, and machine learning with an emphasis on multimodal recognition and security applications. She has authored numerous publications in top journals and conferences, contributing to advancements in fields like emotion-aware de-identification, generative adversarial networks, and ethical AI frameworks in healthcare. Her work spans social behavioral biometrics, gait recognition, masked face recognition, and aesthetic-based person identification. Key contributions include frameworks for ethical AI in care systems, fusion algorithms for multi-biometric systems, and innovations in visual and audio signal processing. Collaborations with experts like Osvaldo Gervasi, Jon G. Rokne, and Padma Polash Paul highlight her interdisciplinary approach. Publications emphasize practical applications such as privacy-preserved biometrics, emotion detection from social media, and adaptive systems for template aging. Despite no explicit mention of grants or labs, her extensive co-author network and frequent citations indicate significant academic influence.

• Vehicular Networks
• Edge Computing
• IoT Security
• +۵ مورد دیگر

Hussein T. Mouftah is a Professor at the University of Ottawa , affiliated with the College of Engineering and Computer Science and the Department of Electrical and Computer Engineering . He is a leading figure in Intelligent Transportation Systems , Wireless Networks , and Smart Cities research. His research spans vehicular ad hoc networks (VANETs) , autonomous electric vehicles (CAEV) , edge computing , IoT security , and 5G/6G-enabled infrastructure . He pioneers dynamic wireless charging , deep reinforcement learning , and federated learning for mobility solutions. The 15 most recent articles highlight his work in edge computing (4 entries), vehicular networks (5 entries), machine learning (3 entries), and blockchain (2 entries), with sub-fields including UAV energy management , real-time task offloading , multi-modal fusion , and smart grid integration . His methodology combines deep RL for autonomous driving , federated learning for decentralized energy trading , and blockchain to secure ITS systems . He collaborates extensively with researchers like Parisa Fard Moshiri , Burak Kantarci , and Binod Vaidya on smart city infrastructure and vehicular security projects.

Marcus Vetterمشاهده پروفایل

استاد

• Deep Learning
• Medical Technology
• Embedded Systems
• +۴ مورد دیگر

Prof. Dr. Marcus Vetter is the founder and director of the Institute for Applied Artificial Intelligence and Robotics (A²IR) at Mannheim University of Technology's Faculty of Information Technology. His work bridges Deep learning Medical imaging and navigation Embedded systems Real-time computing Software engineering for medical devices He has taught courses including Deep Learning Methods, Image-Guided Medicine, and Embedded Systems. Education Computer Science, Technical University of Mannheim, 1999 Doctorate ('summa cum laude superato') in 'Image-based navigation systems', University of Heidelberg, 2003 Research focuses on AI-driven medical imaging tools, real-time deformation models, and open-source frameworks like MITK. His 15 most recent publications span 6D pose estimation for medical robotics Spectroscopy-based diagnostics Formal software verification Gesture and gaze recognition interfaces UAV drive train optimization Scientific achievements Doctorate with distinction (2003) Co-founder of MITK open-source project Director of A²IR institute since 2007 He has received BMBF grants for real-time deformation models and tracking systems, and has led development of navigation systems for laparoscopic surgery and cardiac ablation procedures.

• Wireless Communication
• Machine Learning
• Signal Processing
• +۴ مورد دیگر

Prof. Dr. Haris Gačanin is a faculty member at RWTH Aachen University, affiliated with the Institute for Distributed Signal Processing under the College of Electrical Engineering. His research focuses on integrating machine learning with wireless communication systems, particularly in industrial IoT, edge computing, and network optimization. Current academic rank: Professor Contact: harisg@dsp.rwth-aachen.de Research Interests: Wireless systems, machine learning, signal processing, and network optimization. Key contributions include: Adaptive resource allocation in IIoT and vehicular networks AI-driven channel estimation and feedback mechanisms Security-oriented emitter identification via metric learning Federated/transfer learning for edge environments Hardware-efficient deep learning models for mmWave and THz communications Methodological Focus: Combines reinforcement learning, attention mechanisms, and robust neural architectures with practical implementations on FPGA and vehicular systems.

• Indoor Localization
• Wireless Networks
• Pervasive Computing
• +۱۱ مورد دیگر

Shueng-Han Gary Chan is a faculty member in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), within the College of Engineering. He is actively engaged in research and mentoring, with a strong publication record in mobile computing, indoor localization, and AI for pervasive systems. His research focuses on indoor localization using Wi-Fi, geomagnetic, and inertial signals , sensor fusion , crowd counting with deep learning , domain adaptation , and efficient mobile AI systems . His work bridges theoretical innovation with real-world deployment, as seen in systems for missing person search and indoor navigation. Recent publications (2023–2025) show a consistent trend toward self-supervised and domain-agnostic learning , efficient model design for mobile devices , and robust signal fusion in noisy environments . His team leverages transformer architectures, graph neural networks, and novel optimization techniques to solve real-world challenges in urban and indoor spaces. He has advised numerous graduate students, including Jierun Chen, Zhuoxuan Peng, and Tianlang He, who have contributed as first authors to joint publications. His collaborations span institutions and include work on large-scale system deployments and mobile AI. He leads a research group focused on mobile and pervasive computing , with projects involving IoT-based contact tracing, indoor navigation (e.g., DeepNavi, SiFu), and real-time localization systems. The team emphasizes practical deployment and system robustness.

• Intelligent Transportation Systems
• Connected and Autonomous Vehicles
• Vehicular Networks
• +۶ مورد دیگر

Daxin Tian is a prominent professor at Beihang University's School of Transportation Science and Engineering, specializing in intelligent transportation systems and vehicular networks. With over 170 publications spanning from 2006 to 2025, his research has significantly contributed to the advancement of connected and autonomous vehicle technologies. His work appears consistently in top-tier IEEE journals including IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Intelligent Vehicles, and IEEE Internet of Things Journal, establishing him as a leading authority in the field. Professor Tian's research interests encompass several critical areas in modern transportation technology: Connected and Autonomous Vehicle Systems Vehicular Networking and Communication Protocols Vehicle Platooning and Cooperative Driving Algorithms Edge Computing Applications for Transportation Computer Vision for Autonomous Driving Perception Traffic Flow Optimization and Prediction Models Resource Allocation in Vehicular Networks His recent publications demonstrate an increasing sophistication in addressing complex multi-vehicle scenarios while maintaining practical considerations like communication reliability, energy efficiency, and safety constraints. The research trajectory shows a clear evolution from foundational networking and control problems toward more integrated AI-driven solutions that combine computer vision, natural language processing, and advanced control theory for next-generation transportation systems. Professor Tian maintains extensive international collaborations, particularly with researchers at Canadian institutions including Victor C. M. Leung's group, while leading a substantial research team at Beihang University. His work frequently bridges theoretical advances with practical transportation challenges, resulting in numerous high-impact publications that address real-world implementation barriers in intelligent transportation systems.

• Geoinformatics
• Cartography
• Geodetic Science
• +۵ مورد دیگر

Prof. Monika Sester is a distinguished Professor and Executive Director of the Institute of Cartography and Geoinformatics at Leibniz University Hannover, within the Faculty of Civil Engineering and Geodetic Science. She also serves as Spokesperson for the Leibniz Research Center FZ:GEO and holds multiple leadership roles including Faculty Information Officer (FIO) for the Faculty of Civil Engineering and Geodetic Science, Ombudsman for Good Scientific Practice, and Exchange Coordinator for Geodetic Science and Geoinformatics. Her research focuses on the intersection of geospatial information science, cartography, and urban mobility. Prof. Sester's work spans several key areas: Geospatial data processing and analysis Cartographic representation and visualization Urban mobility and transportation systems Spatial data uncertainty and quality Digital mapping technologies and applications Historical map analysis and interpretation Prof. Sester's recent publications demonstrate a strong focus on applying advanced computational techniques to geospatial problems. Her work shows increasing emphasis on machine learning applications for map analysis, urban mobility optimization, and 3D spatial modeling. She has been particularly active in researching applications of deep learning for historical map interpretation, urban mobility patterns, and spatial uncertainty visualization. Her contributions to the field have been recognized through leadership positions in major research initiatives: Executive Director, Institute of Cartography and Geoinformatics Spokesperson, Leibniz Research Center FZ:GEO Faculty Information Officer, Faculty of Civil Engineering and Geodetic Science Ombudsman for Good Scientific Practice Member of multiple academic committees including the Admissions and Examination Board Prof. Sester actively collaborates with students and researchers across multiple projects focused on geospatial information systems, urban mobility, and cartographic visualization. Her leadership extends to guiding research directions within the Leibniz Research Center FZ:GEO, which brings together interdisciplinary expertise to address complex spatial challenges.

Lukas Hermannمشاهده پروفایل

پژوهشگر

• Robot Learning
• Deep Reinforcement Learning
• Self-Supervised Learning
• +۳ مورد دیگر

Lukas Hermann is a PhD researcher at the Autonomous Intelligent Systems group within the Department of Computer Science at the University of Freiburg. He collaborates with Prof. Dr. Wolfram Burgard and Prof. Thomas Brox, focusing on robot learning and autonomous systems . University of Freiburg: 2011–2019 (B.Sc. and M.Sc. in Computer Science) Current role: Researcher in Robotics & AI (since 2020) Research Interests: Robot Learning Deep Reinforcement Learning Self-Supervised Learning Language-Conditioned Policy Learning Sim-to-Reality Transfer Article Trends: Lukas's publications focus on language-driven robotic imitation learning, adaptive curriculum generation for sim-to-real transfer, and unsupervised dynamics modeling. His work addresses challenges in autonomous manipulation, visual servoing, and data-efficient policy learning using optical flow and structured representations. Projects: CALVIN: Benchmark for language-conditioned long-horizon tasks FlowControl: Optical flow-based visual servoing Bike Navigation in Rome: Safe/easy route planning Adaptive Curriculum Generation for Sim-to-Real Vision-Based Robotic Manipulation with Natural Policy Gradients

• Artificial Intelligence
• Machine Learning
• Internet of Things (IoT)
• +۵ مورد دیگر

G. Thippa Reddy is a prolific researcher with a focus on advanced technologies such as artificial intelligence, machine learning, and blockchain, particularly in healthcare, IoT, and cybersecurity domains. His work spans interdisciplinary areas including federated learning, edge computing, and smart city infrastructure. He has collaborated extensively with researchers like Praveen Kumar Reddy Maddikunta, Gautam Srivastava, and Mamoun Alazab, producing over 150 publications in high-impact journals like IEEE Access, IEEE Internet Things Journal, and IEEE Transactions on Industrial Informatics. His research emphasizes practical applications of AI in real-world scenarios, such as privacy-preserving medical systems, secure UAV networks, and inclusive education for individuals with disabilities. He explores cutting-edge topics like the Metaverse's role in Industry 5.0, blockchain-enhanced security frameworks, and the integration of large language models into intelligent transportation systems. Key contributions include frameworks for federated learning in healthcare, optimized routing protocols for underwater communications, and explainable AI (XAI) methods for industrial automation. His work often addresses challenges in scalability, privacy, and ethical deployment of emerging technologies.