Find Academic Supervisors

• Computer Vision
• Robotics
• 3D Reconstruction
• +5 more

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.

• Computer Vision
• Artificial Intelligence
• Multimodal Learning
• +4 more

Ke Yan is an Associate Professor in the Department of Computer Science at the National University of Singapore's College of Design and Engineering. With extensive research output from 2021-2026, their work spans computer vision, artificial intelligence, and multimodal learning systems. National University of Singapore (Primary Affiliation) Collaborations with University of Electronic Science and Technology of China Research ties with Tencent Youtu Lab in Shanghai Research focuses on advancing computer vision techniques, particularly in medical image analysis, vision-language integration, and fault diagnosis systems. Their work bridges theoretical AI development with practical applications in healthcare, industrial systems, and environmental monitoring. Notable contributions include novel approaches to multimodal learning, medical image segmentation with sparse annotations, and improving reliability of large vision-language models. Recent publication trends (2024-2026) demonstrate increasing focus on multimodal systems, with significant contributions to vision-language model reliability, medical AI applications, and efficient transfer learning techniques. Their work frequently addresses critical challenges like hallucination mitigation in large models and sparse data scenarios in medical imaging. As an advisor, they mentor multiple researchers including Junlong Du, Shouhong Ding, and Zhiwen Lin, with whom they frequently collaborate on cutting-edge computer vision projects. Their research group maintains strong industry connections, particularly with Tencent's AI research division. The research is conducted within NUS's computer vision and AI research ecosystem, collaborating with multiple laboratories focused on multimodal intelligence and practical AI deployment in real-world systems.

• Philosophy Education
• Moral Psychology
• Philosophy of Mind
• +3 more

Dr. Gregor Hochstetter serves as a Lecturer in Subject Didactics for Philosophy/Ethics at the University of Tübingen , within the Department of Philosophy under the Faculty of Humanities. His research focuses on moral psychology, philosophy education, digitalization in teaching, and sustainability in learning environments. He contributes to advancing pedagogical approaches in ethics and philosophy through innovative methodologies, including digital tools and sustainable architectural designs for educational spaces. Key publications include explorations of moral reasoning in education, creativity in philosophy teaching, and embodied cognition studies. Hochstetter has also reviewed significant works in philosophy of mind and cognitive science. His work bridges theoretical philosophy with practical educational challenges, emphasizing interdisciplinary approaches. While no specific grants or advising roles are detailed here, his academic output reflects a commitment to both scholarly research and impactful educational practices. The University of Tübingen’s Department of Philosophy provides a robust academic environment for his contributions to philosophical pedagogy and ethics.

Yan XiaView profile

Researcher

• 3D Vision
• Localization and Navigation
• Robotics
• +2 more

Yan Xia is a Senior Researcher at the Computer Vision Group of the Technical University of Munich (TUM) and a Research Scientist at the Munich Center for Machine Learning. She collaborates with Prof. Daniel Cremers and previously completed her PhD at TUM under supervision of Prof. Uwe Stilla and Prof. Daniel Cremers, with a visiting period at the Visual Geometry Group of the University of Oxford under Dr. João Henriques.

• Large Language Models
• Autonomous Driving
• Computer Vision
• +4 more

Xingcheng Zhou is a Research Assistant at the Technical University of Munich (TUM), affiliated with the Chair of Robotics, Artificial Intelligence and Real-time Systems since 2023. He holds an M.Sc. in Electrical and Computer Engineering from TUM (2021) and previously worked as an Industrial AI Researcher at Siemens. Research Interests: Focus on Large Language Models , Vision Language Models , 3D Environment Perception , and Domain Adaptation in autonomous driving contexts. Publications: Contributions to 3D object detection refinement, sim2real domain adaptation, vision-language models, and dataset development for intelligent transportation systems. Teaching Involvement: Co-supervisor for master's theses and seminars on autonomous agents, perception models, and traffic environment understanding. Advising: Mentoring students on projects including LiDAR-guided monocular detection, world models, and multimodal benchmarks for transportation scenes. Trends in Research: Zhou's work bridges low-light image enhancement with spatial-frequency features, surface-aware frameworks for 3D detection, and weakly-supervised domain adaptation. He contributes to benchmarking spatio-temporal video understanding and evaluating autonomous driving datasets. Supervision and Collaboration: Co-authored key surveys and frameworks with Prof. Alois C. Knoll and peers, focusing on real-time roadside LiDARs, graph-based object relationships, and vision-language integration for traffic analysis.

• Forest Management
• Strategic Management
• Knowledge Management
• +7 more

Dr. Roderich von Detten is an Assistant Professor at the Institute of Forestry Economics, University of Freiburg, specializing in strategic forest management under uncertainty and environmental policy analysis. His career since 2008 has focused on organizational responses to climate change, risk communication, and sustainability concepts in forestry, including leading the DFG-funded project on German forest dieback discourse. He has contributed to knowledge management in forestry through the EU KnowForAlp network and BMBF Waldzukünfte 2100 project. Education Forest Sciences Diplom-Forstwirt (1995), Albert-Ludwigs-Universität Freiburg PhD in Environmental Sciences (2001), University of Freiburg His research integrates strategic management , risk communication , and environmental discourse analysis , with recent work examining adaptive forest governance, climate heroism narratives, and post-normal environmental policy frameworks. Article analysis reveals thematic focus areas spanning climate risk modeling , forest sector identity transformation , and environmental decision support systems .

Daniele CattaneoView profile

Researcher

• Autonomous Robots
• Deep Learning for Localization
• Sensor Fusion
• +3 more

Dr. Daniele Cattaneo is a Junior Research Group Leader at the Robot Learning Lab (University of Freiburg, Germany). He specializes in autonomous robotics, deep learning for perception and localization, and sensor fusion. His research focuses on embodiment-agnostic and environment-agnostic systems for robots, with applications in autonomous driving and healthcare robotics. Education: Ph.D. in Computer Science, Università degli Studi di Milano-Bicocca (2016–2020) M.Sc. and B.Sc. in Computer Science, Università degli Studi di Milano-Bicocca (2013–2016, 2010–2013) Research Interests: His work addresses challenges in LiDAR-camera calibration, SLAM (Simultaneous Localization and Mapping), unsupervised domain adaptation, and multimodal fusion for robust perception. Key projects include CMRNext (LiDAR-camera matching), Syn-Mediverse (healthcare scene understanding), and Continual SLAM (long-term autonomy). Awards & Grants: He leads funded projects like AI-Drive (next-gen autonomous driving algorithms) and iSUOR (operating room video analysis). Collaborations include work with the AIS Group and Robotic Learning Lab . Students & Labs: Supervises 12+ students in topics like LiDAR localization, HD maps, and radar-based navigation. Active in the Robot Learning Lab at Freiburg, contributing to open-source datasets and tools for robotics research.

Katherine StorrsView profile

Senior Lecturer

• Visual perception
• Deep learning
• Psychophysics
• +7 more

Katherine Storrs is a Senior Lecturer in the School of Psychology at the University of Auckland, New Zealand. She leads the Computational Perception Lab, where she combines computational modeling and psychophysical experiments to study visual perception. Her research is supported by a Marsden Fast Start grant, and she is actively involved in teaching and academic service. She earned her PhD in Psychological Science from the University of Queensland in 2015 and has held postdoctoral positions at Justus-Liebig University (Germany) and the MRC Cognition and Brain Sciences Unit (Cambridge, UK). She also worked as a Data Scientist at Twitter in London. Dr. Storrs' research focuses on how the visual system interprets material properties such as gloss, shape, and reflectance. She uses unsupervised deep learning models to simulate and predict human perception, particularly in ambiguous or complex visual environments. Her work bridges cognitive science, neuroscience, and artificial intelligence. Her most recent publications explore topics such as gloss perception, mental rotation, face similarity, and the role of statistical learning in shape encoding. These works frequently appear in high-impact journals like Nature Human Behaviour , PNAS , and Current Biology , demonstrating a strong trend toward using computational models to explain perceptual phenomena. Marsden Fast Start Grant (2021) Humboldt Research Fellowship (2019) UK National Finalist, FameLab (2017) Editorial Board Member, Nature Communications Psychology (2023–) Editorial Board Member, OpenMind (2022–) Social Media Editor, Perception and i-Perception (2020–) She supervises graduate students and teaches courses including PSYCH 306 (Research Methods), PSYCH 775 (Visual Perception in Brains and Machines), and PSYCH 109. She also mentors students in honours, master's, and PhD programs. Her lab is actively involved in interdisciplinary collaborations, particularly with researchers in machine learning and computational neuroscience. The lab is funded by the Marsden Fund and supported by access to high-performance computing resources for training deep neural networks.

Stephen KobourovView profile

Professor

• Algorithm Design
• Computational Geometry
• Graph Drawing
• +3 more

Prof. Stephen Kobourov is a Professor in the TUM School of Computation, Information and Technology at Technische Universität München (TUM). Previously, he held positions at the University of Arizona from 2000 to 2024, progressing from Assistant Professor to Full Professor, and served as Deputy Director of the Data Science Institute. His expertise lies in algorithm design, computational geometry, and graph visualization, with over 250 publications and significant funding from NSF, ONR, and USDA grants. Education: BS in Computer Science and Mathematics from Dartmouth College (1995), PhD in Computer Science from Johns Hopkins University (2000). Research focuses on efficient algorithms for graph drawing, visualization techniques for networks, and geometric algorithms. Notable contributions include work on stress metrics in graph layouts, hypergraph representations, and non-Euclidean visualization frameworks. He has co-chaired committees for ALENEX, IEEE PacificVis, and GD, and serves as an editor for JGAA, CGTA, and IEEE TVCG. Awards include the Fulbright Distinguished Chair (2015–2016), Humboldt Research Fellowship (2011–2014), and NSF Career Award (2006–2011). His recent work explores multi-layer network visualization, AI-driven graph analysis (e.g., MLLMs perception), and graph embeddings in non-Euclidean spaces. Advising and grants: Extensive grants from NSF and other agencies support his research. He has advised numerous students and collaborates internationally, contributing to labs like the Data Science Institute and initiatives such as the Institutional Knowledge Map (KMAP). Visualization projects include MetroSets (metro map-style set visualization), Wooly Graphs (knitting pattern frameworks), and tools for interactive network analysis. His work bridges theoretical algorithms with practical applications in science and technology.

Hu CaoView profile

Researcher

• Autonomous Driving
• Robotic Grasping
• Medical Image Analysis
• +5 more

Hu Cao is a postdoctoral research associate at the Chair of Robotics, Artificial Intelligence and Real-Time Systems (Prof. Alois Knoll) at the Technical University of Munich (TUM) . Holding a Ph.D. from TUM, his research bridges autonomous driving , robotic grasping , medical image analysis , and dense prediction (classification, detection, segmentation). Education : Ph.D. from TUM Hu's work explores: Autonomous Driving : Perception under adverse conditions, multi-sensor fusion, and risk-based safety models Robotic Grasping : Vision-language integration for 6D pose estimation Medical Imaging : Transformer-based segmentation techniques (e.g., Swin-Unet) His recent publications include 15+ works at top venues like CVPR , ICCV , IEEE TPAMI , and IEEE TIV , with 6052+ Google Scholar citations . Notably, Swin-Unet ranks among the top 3 most cited ECCV papers in 5 years, and his work on event-based autonomous driving perception was featured in IEEE Xplore Innovation Spotlight . Editorial roles include: Associate Editor for Visual Intelligence and Frontiers in Neurorobotics Editorial Board member of Artificial Intelligence and Autonomous Systems (AIAS) Topic Editor for Frontiers in Robotics and AI and Frontiers in Neuroscience He has reviewed for 20+ top journals (e.g., Nature Computational Science , IEEE TRO ) and served on program committees for NeurIPS , CVPR , ICCV , and MICCAI .

Christian HeineView profile

Researcher

• Data Visualization
• Topology-Based Methods
• Scientific Computing
• +3 more

Christian Heine is a researcher at the Institute of Computer Science , University of Leipzig. His work focuses on advanced data visualization techniques, particularly those grounded in topological and geometric analysis of scalar fields, ensemble data, and high-dimensional datasets. Key Research Areas: Topological visualization, scalar field analysis, medical imaging, and uncertainty quantification. Methodologies: Bayesian inference, fiber trajectories, volume rendering, and dynamic workflows. Applications: Meteorological data analysis, medical diagnostics, and interactive visualization systems. He has published extensively on these topics, with recent work addressing spatio-temporal trends in climate data and noise-robust visualization techniques. His research often integrates interdisciplinary approaches, bridging computer science and applied sciences.

Claus BrennerView profile

Adjunct Professor

• LiDAR Mapping
• Point Cloud Processing
• Robust Estimation
• +3 more

apl. Prof. Dr.-Ing. Claus Brenner is an Adjunct Professor at the Institute of Cartography and Geoinformatics within the Faculty of Civil Engineering and Geodetic Science at Leibniz University Hannover. His research focuses on LiDAR mapping, point cloud processing, and robust estimation, with applications in autonomous systems, urban mapping, and disaster risk assessment. He leads the Graduiertenkolleg 2159 research group on integrity and collaboration in dynamic sensor networks. Key research areas include 3D reconstruction, SLAM (Simultaneous Localization and Mapping), semantic segmentation of mobile mapping data, and cooperative perception systems. His work integrates advanced machine learning techniques with geospatial data analysis, addressing challenges in sensor fusion, uncertainty modeling, and real-time localization. Recent publications span topics like voxel-based point cloud localization for smart spaces, flood risk mapping using LiDAR, and adversarial shape completion. Brenner has contributed to benchmark datasets such as LuCoop and LUMPI, advancing research in cooperative perception and urban navigation. His methods emphasize robustness and scalability, often leveraging generative models and statistical frameworks for urban environment analysis. Notable projects include the development of high-definition mapping using LiDAR, trajectory-based road network reconstruction, and semantic annotation from user trajectories. His work bridges theoretical advancements in computer vision with practical applications in autonomous systems and smart infrastructure.

Peer NeubertView profile

Professor

• Autonomous Robotics
• Artificial Intelligence
• Computer Vision
• +5 more

Peer Neubert is a Professor at the University of Koblenz , appointed in October 2022, and previously a senior researcher (Dr.-Ing.) in the Automation Technology group at TU Chemnitz . His work lies at the intersection of autonomous robotics , computer vision , and machine learning , with particular expertise in place recognition in changing environments and hyperdimensional computing . His research spans: Vector Symbolic Architectures and hyperdimensional representations for robotics, Visual place recognition robust to seasonal and illumination changes, Neurologically inspired navigation models (e.g., grid-cell representations), Deep learned and hand-crafted image descriptors for mobile robot localization, Efficient graph optimization and SLAM techniques. Since 2010 he has published extensively in RSS , ICRA , CVPR , IEEE RA-L , and other premier venues, with a clear trend toward unsupervised, memory-efficient, and biologically inspired solutions. In 2022 he was nominated for the Heinz Maier-Leibnitz Prize by the Deutsche Forschungsgemeinschaft. No advisees or direct contact details are provided in the source material.

Hao XingView profile

Researcher

• Robot Vision
• Human Action Recognition
• Human-Object Interaction Recognition
• +4 more

Hao Xing is a scientific researcher and post-doctoral fellow at the Institute for Cognitive Systems (ICS), Technical University of Munich (TUM), working with Prof. Gordon Cheng since May 2024. Previously, he served as a research assistant at the Munich Institute of Robotics and Machine Intelligence (MIRMI) and completed his PhD under Prof. Darius Burschka from 2019. His educational background includes: Master of Science in Mechanical Engineering from Technical University of Munich Bachelor of Engineering in Mechanical Engineering from Hefei University of Technology, China Xing's research focuses on Robot Vision , Human Action Recognition , and Graph Convolutional Networks , with significant contributions to Human-Object Interaction Recognition , Scene Understanding , and Visual Depth Estimation . His work leverages machine learning to develop robust algorithms for human activity analysis and robotic perception, emphasizing spatio-temporal modeling and uncertainty handling in real-world scenarios. Analysis of his 13 recent publications (2019-2025) reveals a dominant focus on graph-based approaches for action recognition and segmentation, with increasing emphasis on open-world applications, uncertainty modeling, and healthcare integration. His research spans computer vision, robotics, and medical applications, demonstrating strong interdisciplinary impact through collaborations in surgical robotics and patient monitoring systems. Xing actively mentors students through master's thesis projects in Stereo Matching, Human Activity Segmentation, and Monocular Depth Estimation, requiring expertise in deep learning frameworks and computer vision algorithms. While no major grants are explicitly mentioned, his thesis topics indicate active research funding in geometric vision and human activity analysis. He operates within the Institute for Cognitive Systems (ICS) at TUM, a key unit in MIRMI's robotics ecosystem focused on advancing human-robot interaction through vision-based scene understanding and motion generation capabilities.

• Artificial Intelligence
• Robotics
• Knowledge Representation
• +3 more

Axel Großmann is a former PhD Researcher affiliated with the International Center for Computational Logic (ICCL) at the Technische Universität Dresden . He was part of the Faculty of Computer Science and the Knowledge Representation and Reasoning Research Group . His work focuses on robotics , particularly in areas such as mobile robot localization, control systems, and probabilistic sensor models. He contributed to integrating reactive control, reasoning, and execution monitoring in dynamic environments. Key research interests include knowledge representation , symbolic dynamic programming , and robot-environment interaction . His publications span topics like semi-supervised learning methods, visual sensor models, and robust localization techniques using Hough transforms and probability grids. He collaborated on technical reports and conference papers addressing autonomous navigation and adaptive control systems. While no awards or current students are explicitly mentioned, his involvement in the ICCL and the Knowledge Representation group highlights his contributions to advancing computational logic and robotics applications. His work integrates theoretical foundations (e.g., Fluent Calculus) with practical robotics challenges.