جستجوی استاد راهنمای دانشگاهی

• Computer Vision
• Computer Graphics
• Machine Learning
• +۱۱ مورد دیگر

Andrea Tagliasacchi is an Associate Professor in the School of Computing Science at Simon Fraser University (SFU), where he holds the Visual Computing Research Chair. He is also a part-time (20%) Staff Research Scientist at Google DeepMind in Toronto and holds an associate professor (status only) appointment in the Department of Computer Science at the University of Toronto. Education: PhD in Computing Science – Simon Fraser University (NSERC Alexander Graham Bell Fellow) Postdoctoral Research – École Polytechnique Fédérale de Lausanne (EPFL) MSc in Computer Science – Politecnico di Milano (Gold Medalist) His research lies at the intersection of computer vision, computer graphics, and machine learning, with a focus on 3D visual perception. Key areas include neural radiance fields (NeRF), 3D Gaussian splatting, inverse rendering, and geometric deep learning, with applications in robotics, augmented reality, and autonomous systems. His work emphasizes robust and efficient scene understanding and reconstruction from visual data. His recent publications, appearing in top venues like CVPR, SIGGRAPH, NeurIPS, and ECCV, demonstrate a strong emphasis on neural fields, 3D reconstruction, and generative modeling. Trends include improving rendering efficiency, enhancing robustness to noise and distractors, and enabling controllable and 3D-aware generation. His group has made significant contributions to Gaussian splatting, NeRF optimization, and diffusion-based 3D/4D synthesis. Scientific Awards: 2024 CVPR Best Paper Award (Honorable Mention) 2020 CVPR Best Student Paper Award 2015 SGP Best Paper Award NSERC Alexander Graham Bell Canada Graduate Scholarship MITACS Best Paper Award (SIGGRAPH Asia 2009) NSF Best Poster Award (SGP 2012) He has advised numerous PhD and MSc students, many of whom are now researchers at leading institutions and companies. His research has been supported through collaborations with Google, Intel, and academic partners. He serves the community as a Senior Area Chair for CVPR 2025, Associate Editor for IEEE TPAMI (2024–2026), Guest Editor for IEEE TPAMI on 3D GenAI, and Program Chair for 3DV 2024. He leads a vibrant research lab at SFU focused on pushing the boundaries of 3D scene understanding with machine learning.

• 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.

• Robotics
• Photogrammetry
• Simultaneous Localization and Mapping (SLAM)
• +۱۲ مورد دیگر

Cyrill Stachniss is a Full Professor at the University of Bonn , where he heads the Lab for Photogrammetry and Robotics and is affiliated with the Lamarr Institute for Machine Learning and Artificial Intelligence . He was previously a Visiting Professor in Engineering at the University of Oxford until 2025. His academic journey includes positions at the University of Freiburg, University of Zaragoza, and the Swiss Federal Institute of Technology. University: University of Bonn School: Faculty of Engineering Department: Department of Photogrammetry Academic Rank: Professor His research spans robotics, photogrammetry, SLAM, autonomous navigation, perception systems, agricultural robotics, and unmanned aerial vehicles . He emphasizes probabilistic techniques for mobile robots and has made significant contributions to visual and LiDAR-based localization, scene understanding, and 3D reconstruction. The recent publications highlight a strong trend toward neural implicit representations, agricultural phenotyping, radar-based perception, and active learning . His team develops robust systems for real-world deployment in dynamic and unstructured environments, particularly in precision farming and autonomous vehicles. Scientific Awards: IEEE RAS Early Career Award (2013) Microsoft Research Faculty Fellow (2010) 7th EURON Georges Giralt Award (2008) Multiple Best Paper Awards at ICRA, IROS, RSS, and RAL Faculty Teaching Award, University of Freiburg He has advised numerous students and leads the DFG Cluster of Excellence PhenoRob and Research Unit FOR 1505 Mapping on Demand . His lab has co-founded three startups, reflecting strong industry and societal impact. He also runs the educational video series 5 Minutes with Cyrill , explaining key robotics concepts.

• Computational Pathology
• Medical Image Analysis
• Deep Learning
• +۴ مورد دیگر

Nasir M. Rajpoot is a Professor in the Department of Computer Science at the University of Warwick, UK. His research focuses on computational pathology, medical image analysis, and deep learning applications in histology. He leads interdisciplinary projects integrating artificial intelligence with healthcare, particularly in cancer diagnostics and pathology workflows. Rajpoot’s work emphasizes developing robust algorithms for histology image analysis, including nuclear segmentation, tumor classification, and domain generalization in computational pathology. His contributions include the TIAToolbox, an open-source framework for tissue image analytics, and the CoNIC Challenge to advance nuclear detection and counting in histology images. He collaborates with clinicians and biologists to translate AI models into clinical practice, addressing challenges like tumor heterogeneity and staining variability. Rajpoot’s research spans colorectal, lung, and oral cancers, with a focus on predicting clinical outcomes via histological features and genomic data integration. Notable projects include the development of Handcrafted Histological Transformer (H2T) for unsupervised representations of whole slide images and the SAFRON framework for histology image synthesis. His work addresses domain adaptation, robustness evaluation, and explainability in AI-driven pathology systems.

• LiDAR-based Perception
• Autonomous Vehicles
• Agricultural Robotics
• +۴ مورد دیگر

Jens Behley is a Lecturer (Privatdozent) and postdoctoral researcher at the Department of Photogrammetry, University of Bonn. He completed his habilitation in 2023 with a thesis on LiDAR-based spatio-temporal scene understanding for autonomous vehicles and earned his PhD in 2014 under Prof. Armin Cremers. His research focuses on LiDAR perception, agricultural robotics, and 3D scene understanding. Behley is an Associate Editor at IEEE Robotics and Automation Letters (RA-L) and has authored influential datasets like SemanticKITTI and BonnBeetClouds3D. Education: PhD in Computer Science, University of Bonn, 2014 Habilitation in Photogrammetry, University of Bonn, 2023 Research Interests: LiDAR-based perception in urban and agricultural environments, machine learning for robotics, semantic mapping, SLAM algorithms, and 3D reconstruction. His work bridges computer vision and robotics, with applications in autonomous vehicles and precision agriculture. Awards: Best Agri-Robotics Paper Award (IROS 2024) Outstanding Reviewer Awards (ECCV, CVPR, ICRA) Faculty Award for Geodesy (2021) Advisees & Grants: Behley collaborates extensively with the PRBonn lab and researchers like Cyrill Stachniss, focusing on projects funded by EU Horizon and industry partners. His team develops open-source tools for LiDAR processing (e.g., KISS-ICP, VDBFusion). Labs/Teams: Part of the Photogrammetry and Robotics Institute (IGG) at the University of Bonn, contributing to the PRBonn research group.

Margret Keuperمشاهده پروفایل

استاد

• Computer Vision
• Machine Learning
• Deep Learning Model Robustness
• +۷ مورد دیگر

Prof. Margret Keuper is a Professor of Machine Learning at the University of Mannheim's School of Business Informatics and Mathematics, leading the Data and Web Science Group. She is also affiliated with the Max-Planck-Institute for Informatics and ELLIS (fellow since 2024). Her research focuses on robust deep learning, neural architecture search, and computer vision tasks like motion segmentation and adversarial defense. She holds a PhD from the University of Freiburg and previously held positions at the University of Siegen and the University of Mannheim. Her work spans projects funded by DFG and BMBF, including Climate Visions for social media analysis and TrackOpt for motion tracking. She teaches courses on computer vision, generative models, and reinforcement learning. She actively serves on program committees for top conferences like CVPR, ECCV, and NeurIPS, and is an associate editor for IEEE TPAMI and JAIR. Education: PhD in Computer Science from University of Freiburg (advisor: Thomas Brox) Research Projects: Learning to Sense (DFG), Climate Visions (BMBF), TrackOpt (BMBF) Key Roles: Head of Mannheim Master in Data Science Examination Board, Member of MSc Business Informatics Board Her research emphasizes robustness in AI systems, with contributions to adversarial attacks, domain generalization, and efficient solvers for large-scale problems. She advises over 15 PhD students across academic and industry partnerships.

• Autonomous Driving
• Sensor Fusion
• Intelligent Transportation Systems
• +۵ مورد دیگر

Prof. Dr.-Ing. Christoph Stiller is a full professor at the Karlsruher Institut für Technologie (KIT) and serves as the director of the Institute of Measurement and Control Technology (Institut für Mess- und Regelungstechnik, MRT). His work focuses on autonomous driving, sensor fusion, probabilistic estimation, HD mapping, motion planning, and intelligent transportation systems. Education: Details on his academic degrees are not provided in the text, but he holds the title of Dr.-Ing. indicating a doctoral degree in engineering. Research Interests: Prof. Stiller's research spans a wide array of topics critical to the development of autonomous vehicles. His work includes: Sensor Fusion: Integrating data from LiDAR, cameras, and radar to create robust perception systems. HD Mapping & Localization: Developing high-definition maps and precise localization techniques for urban and highway environments. Motion Planning & Decision Making: Creating algorithms for safe and efficient trajectory planning under uncertainty. Machine Learning & AI: Applying deep learning and reinforcement learning to perception, prediction, and control tasks. Publication Trends: His recent publications (2023–2025) emphasize robust traffic light detection, image stitching for panoramic views, motion prediction using redundancy reduction, and safety-enhanced model predictive control. The work increasingly integrates learning-based methods with classical control and estimation theory. Scientific Awards: No specific awards are listed in the provided text. Teaching & Supervision: Prof. Stiller teaches foundational and advanced courses in measurement and control systems, probabilistic estimation, and autonomous driving. He holds regular office hours during both summer and winter semesters and is actively involved in advising students and researchers. Labs & Teams: He leads the Institute of Measurement and Control Technology (MRT) at KIT, which is engaged in cutting-edge research in autonomous systems. The institute collaborates with industry and academia on large-scale projects such as UNICARagil and various European initiatives.

Xieyuanli Chenمشاهده پروفایل

دانشیار

• Robotics
• Autonomous Systems
• Computer Vision
• +۳ مورد دیگر

Xieyuanli Chen is an Associate Professor at the National University of Defense Technology (NUDT), China. He holds a Dr.-Ing. (summa cum laude) from the University of Bonn (2022), a Master's in Robotics from NUDT (2017), and a Bachelor's in Electrical Engineering from Hunan University (2015). His research focuses on robot learning, perception, and navigation, with an emphasis on LiDAR-based SLAM, autonomous systems, and semantic perception. Education: PhD: University of Bonn, 2018-2022 (supervised by Prof. Cyrill Stachniss) Master's: NUDT, 2015-2017 Bachelor's: Hunan University, 2011-2015 Research interests include robotics, autonomous systems, computer vision, and LiDAR perception. He has authored over 90 papers in top venues like TRO, RSS, ICRA, and CVPR. He serves as an Associate Editor for IEEE RA-L, ICRA, and IROS, and is a member of the RoboCup Rescue Robot League Technical Committee. Awards include the RSS Pioneer Award (2021), Best-in-Class RoboCup awards, and recognition as a World’s Top 2% Scientist (2024). His work spans LiDAR localization, moving object segmentation, and efficient semantic mapping. He advises students in robotics and autonomous systems. Labs/Teams: Active in the PRBonn group (University of Bonn) and leads research at NUDT on LiDAR-based perception systems.

• Medical Image Analysis
• Machine Learning
• Multiple Instance Learning
• +۳ مورد دیگر

Ario Sadafi is a researcher at the Technical University of Munich (TUM) , affiliated with the Chair of Computer Science Applications in Medicine under Prof. Nassir Navab. His work spans medical image analysis , machine learning , and computational pathology , with a strong focus on developing AI-driven solutions for microscopic imaging in hematology and oncology. Research Focus: Multiple Instance Learning for weakly supervised medical image classification. Explainable AI for biomedical single-cell imaging. Continual and cross-domain learning for robust diagnostic models. Microscopic image analysis for blood cell disorders and leukemia subtyping. Teaching Contributions: Sadafi has been actively involved in teaching courses such as Computer Aided Medical Procedures , Medical Augmented Reality , and Deep Learning for Medical Applications . He also supervises practical courses and seminars in 3D Computer Vision and Machine Learning in Medical Imaging . Labs & Collaborations: He works closely with the MEDIA (Medical Image Analysis) and NARVIS labs at TUM, contributing to projects in surgical data science , generative models , and robotics & ultrasound . Publications Impact: His research output (2018–2025) emphasizes AI-driven hematology , with applications in red/white blood cell classification, leukemia subtype diagnosis, and interpretable deep learning models for clinical use.

• Artificial Intelligence
• Decision-Making Systems
• Fuzzy Logic
• +۵ مورد دیگر

Núria Agell Jané is a Full Professor at ESADE Business School , Universitat Ramon Llull, specializing in Artificial Intelligence and Decision-Making Systems. She leads the JUICE (Judgements and Decisions in the Market Place) research group and the ESADE D3 - Institute for Data-Driven Decisions . Doctorate in Applied Mathematics (Qualitative Reasoning Modelling), UPC-BarcelonaTech Bachelor's in Mathematics, University of Barcelona Her research focuses on Artificial Intelligence , Decision-Making Systems , and Fuzzy Logic , with applications in Business, Marketing, and Sustainability. Recent publications emphasize Hesitant Fuzzy Linguistic Term Sets , Consensus Modeling , and AI in Sustainable Development . She coordinates multiple publicly and privately funded projects applying AI to Business and Marketing challenges. As PhD Programme Director (2005-2013) and current Department Director of Operations, Innovation and Data Sciences , she has shaped academic and research strategies at ESADE. Her work spans collaborations with institutions like LAAS-CNRS (France) and University of Edinburgh Business School , with over 40 journal publications and 50 conference contributions. She has directly supervised 11 PhD students in AI and Decision Sciences.

Guillermo Gallegoمشاهده پروفایل

استاد

• Robotics
• Computer Vision
• Event-based Vision
• +۵ مورد دیگر

Guillermo Gallego is a Professor of Robotic Interactive Perception at the Faculty of Electrical Engineering and Computer Science , Technische Universität Berlin , holding the Einstein Center Digital Future (ECDF) Professorship since 2019. His research bridges robotics , computer vision , and applied mathematics , focusing on optimization methods for interdisciplinary imaging and control problems. Education : PhD in Electrical and Computer Engineering (Georgia Tech, 2011), MS in Mathematics (Georgia Tech, 2009), MS in Electrical Engineering (Georgia Tech, 2007), MS in Mathematical Engineering (Universidad Complutense de Madrid, 2005). Gallego's work explores event-based vision to enhance robot perception through low-latency sensing and real-time 3D reconstruction . He previously held postdoctoral positions at the Institute of Neuroinformatics (University of Zurich/ETH Zurich) and Technical University of Madrid (Marie Curie Experienced Researcher). His interdisciplinary projects span applications in ocean remote sensing , autonomous driving , and space exploration . Key scientific awards include the Fulbright Fellowship (2005-2010) and Marie Curie Experienced Researcher (2011-2014). His recent publications focus on event camera algorithms for optical flow , SLAM , and noise estimation , reflecting his leadership in event-based vision research. Collaborations include institutions like University of Zurich , Georgia Tech , and University of Pennsylvania . Research Grants : Funded through ECDF and Marie Curie programs. Labs : Affiliated with the Einstein Center Digital Future and Institute of Neuroinformatics (Zurich/ETH Zurich).

Volker Rodehorstمشاهده پروفایل

استاد

• Computer Vision
• Image Analysis
• 3D Reconstruction
• +۵ مورد دیگر

Univ.-Prof. Dr.-Ing. habil. Volker Rodehorst is a full professor of computer vision at Bauhaus-Universität Weimar, holding positions in both the Faculty of Media and Faculty of Civil Engineering. His research focuses on photogrammetric computer vision, image analysis, 3D reconstruction, and structural health monitoring with applications in civil infrastructure inspection and urban modeling. He leads projects like ev.AI.luate and InfraCloud, leveraging AI and UAS technologies for infrastructure assessment. Education: PhD (2003): Technical University of Berlin, Faculty of Civil Engineering & Applied Geosciences Habilitation (2013): TU Berlin, Faculty of Electrical Engineering & Computer Science Computer Science Diploma (1994): TU Berlin Research Interests: UAS-based structural inspection using multi-view stereo and deep learning Crack detection and segmentation in concrete structures Automated building age estimation for energy modeling Flight path planning optimization for complex structures Integration of computer vision into BIM workflows Publications: Recent work emphasizes robust algorithms for crack detection (Omnicrack30k benchmark), UAS flight path optimization, and semantic segmentation challenges in bridge inspections. Key contributions include MVCrackViT and CISOL datasets advancing structural analysis methodologies. Awards: Best Academic Performance Prize (1994) - TU Berlin ISPRS Presidential Citation (2008) for WG III/2 leadership Grants & Labs: Leads Bauhaus' 3D-RealityCapture-ScanLab and coordinates EU projects like AISTEC-PRO. Active in developing modular solutions like smoodPLAN for infrastructure inspection. Teaching: Offers courses in photogrammetric computer vision, geodesy, and parallel systems. Supervises PhD students in structural health monitoring and computer vision.

Bashir Kazimiمشاهده پروفایل

پژوهشگر

• Deep Learning
• Computer Vision
• Materials Science
• +۳ مورد دیگر

Dr.-Ing. Bashir Kazimi is a group leader at the Materials Data Science and Informatics (IAS-9) department within the Institute for Advanced Simulation at Forschungszentrum Jülich. His work focuses on advancing deep learning and computer vision techniques for electron microscopy data analysis, enabling efficient material characterization. Expertise: Deep Learning, Computer Vision, Image Analysis Collaboration: Works closely with the Ernst-Ruska-Center (ER-C) for electron microscopy expertise Research Interests: Bashir develops and applies deep learning methods for tasks such as denoising, super-resolution, semantic segmentation, and tracking in electron microscopy. His applications span nanomaterial characterization, crystallographic defect identification, and orientation mapping. Scientific Trends: His recent publications highlight advancements in self-supervised learning, semantic segmentation of TEM images, and applications of deep learning to both materials science and archaeological monument detection in geospatial data. Scientific Achievement: Admitted to the Young Excellent Scientist Program (YESP) in 2024, supporting leadership development and scientific visibility Advising: Supervises Shrindhi Bhat , a PhD student in his group. He is involved in projects like FAST-EMI (Deep-learning assisted fast in situ 4D electron microscope imaging), with a focus on enhancing materials analysis through AI.

Yu Kangمشاهده پروفایل

استاد

• Precision Agriculture
• Remote Sensing
• Plant-Environment Interactions
• +۳ مورد دیگر

Prof. Yu Kang is a Professor of Precision Agriculture at the TUM School of Life Sciences, Technische Universität München (TUM). His research focuses on integrating imaging, sensing, and computational methods to study plant-environment interactions. He aims to enhance resource efficiency and reduce environmental impact through precision crop management. Prior to TUM, he held positions at China Agricultural University (CAU) and conducted postdoctoral research at ETH Zurich and KU Leuven. Prof. Yu's career includes roles such as Associate Professor of Crop Science at CAU and postdoctoral fellowships in physical geography. His educational background includes a doctoral degree from the University of Cologne (2014) and undergraduate studies at China Agricultural University. Key research areas include remote sensing for crop health monitoring, hyperspectral imaging for disease detection, and machine learning applications in agriculture. His work has led to innovations in crop nitrogen management and precision phenotyping. Awards include the Innovation Team Award (2019) from the Crop Science Society of China and the GSGS Fellowship (2014) from the University of Cologne.

• Computer Vision
• Robotics
• 3D Reconstruction
• +۵ مورد دیگر

Thomas Läbe is a Researcher in the Department of Photogrammetry at the University of Bonn's Institute of Geodesy and Geoinformation. His roles include technical associate and software developer, with a focus on advancing robotics, computer vision, and agricultural automation. He holds a diploma in computer science (Dipl.-Inform. (FH)) from Cologne University of Applied Sciences (1994). His research spans image processing, bundle adjustment, visual odometry, and camera calibration, with notable contributions to SLAM (Simultaneous Localization and Mapping) for autonomous systems. Education: 1994: Dipl.-Inform. (FH) in Computer Science, Cologne University of Applied Sciences Research Interests: Focuses on integrating vision-based technologies into robotics for precision agriculture, 3D reconstruction, and robust localization in dynamic environments. His work addresses challenges in sensor calibration, panoptic segmentation, and semantic mapping for autonomous systems operating in agricultural and urban settings. Publications Trends: Recent work emphasizes agricultural robotics, including fruit completion, plant phenotyping, and robust localization under changing conditions. Key themes include LiDAR-based localization, semantic occupancy prediction, and end-to-end learning for 3D representations. Awards: 2001 Hansa Luftbild Price (Best PFG paper award, shared) Technical Contributions: Developed software frameworks for bundle adjustment, multi-camera systems, and obstacle detection. Collaborated on projects like the Phenoliner field phenotyping platform and UAV-based environmental monitoring systems. Labs/Teams: Active in the Photogrammetry professorship group, contributing to the PRBonn (Perception, Robotics & Bonn) robotics initiatives, with open-source tools like OverlapNet and PAg-NeRF for 3D perception.