جست‌وجوی استاد و پژوهشگر

Maolin Gaoمشاهده پروفایل

پژوهشگر

• Computer Vision
• 3D Shape Matching
• Geometry Processing
• +۵ مورد دیگر

Maolin Gao is a Researcher at the Computer Vision Group , TUM School of Computation, Information and Technology , and a PhD candidate at the Department of Informatics 9 , Technical University of Munich (TUM). He is supervised by Prof. Daniel Cremers and was a visiting scholar at Stanford University's Geometric Computing Lab under Prof. Leonidas J. Guibas in Summer 2024. Education : Bachelor in Physics from Tongji University (Shanghai), with exchange experience at TUM and RWTH Aachen Master's in Electrical Engineering and Information Technology from TUM, thesis on Blind Deconvolution supervised by Dr. Michael Hirsch, Prof. Philipp Hennig, and Prof. Bernhard Schölkopf at Max Planck Institute for Intelligent Systems (MPI-IS) in Tübingen Research Focus : Maolin's work bridges geometry and learning to enhance human and machine understanding of 2D/3D data. His research spans 3D shape matching , non-rigid correspondence , geometric consistency , and deep learning applications in computer vision and graphics. He also explores photometric stereo , bundle adjustment , and scale-invariant matching methods . Article Trends : His publications emphasize 3D shape analysis , including partial-to-partial matching , non-rigid deformations , and geometric consistency algorithms . Recent works like EchoMatch (CVPR 2025) and CoE (3DV 2025) highlight advancements in point cloud correspondences and cycle-consistency . Earlier papers address distributed optimization (3DV 2020) and isometric multi-shape matching (CVPR 2021). Scientific Awards : Oral Presentation Award at 3DV 2020 for Distributed Photometric Bundle Adjustment Labs & Collaborations : Affiliated with TUM CVAI Lab and Stanford Geometric Computing Lab . Collaborates with researchers like Prof. Florian Bernard and Dr. Michael Hirsch.

Aljaž Božičمشاهده پروفایل

پژوهشگر

• Computer Vision
• Computer Graphics
• Artificial Intelligence
• +۷ مورد دیگر

Aljaž Božič is a Research Scientist at Meta Reality Labs Research , focusing on neural rendering, 3D reconstruction, and AI-driven geometry modeling. He earned his Ph.D. in Computer Science from the Technical University of Munich (TUM) and holds a Master's in Computer Science from TUM and a Bachelor's in Mathematics from the University of Ljubljana . His research spans computer vision, graphics, and artificial intelligence , with a focus on neural rendering , generative AI , and 3D deformable object modeling , targeting applications in VR/AR and robotics. His work includes time-consistent dynamic scene reconstruction (SceNeRFlow), volumetric hair appearance modeling, and high-fidelity walkable VR spaces (VR-NeRF), alongside efficient NeRF distillation and calibration methods (Neural Lens Modeling). Key article trends include Transformer-based monocular reconstruction (TransformerFusion), neural parametric shape models (NPMs), and self-supervised non-rigid tracking (Neural Deformation Graphs). He has contributed to open-source projects like the TransformerFusion GitHub repository , emphasizing MIT-licensed tools for scene reconstruction. At TUM, he served as a Teaching Assistant for courses such as 3D Scanning and Spatial Learning and 3D Vision Seminar , bridging academic instruction with research innovation. His work integrates advanced neural networks with practical optimization techniques, advancing fields like RGB-D reconstruction (DeepDeform) and variational SLAM.

Xu Chenمشاهده پروفایل

پژوهشگر

• 3D Generative Models
• Computer Vision
• Human Activity Simulation
• +۵ مورد دیگر

Xu Chen is a doctoral researcher at ETH Zurich specializing in 3D generative models and neural implicit shape animation . His work focuses on creating photo-realistic simulations of human activity for applications in human-centric perception tasks .

Jon Sporringمشاهده پروفایل

استاد

• Computer Science
• Mathematical Image Processing
• Medical Image Analysis
• +۶ مورد دیگر

Jon Sporring is a Professor at the Department of Computer Science, University of Copenhagen, specializing in theoretical and applied image processing, stochastic geometry, and biomedical imaging. He leads research in mathematical and medical image analysis, computer graphics, and pattern recognition. Education: Ph.D. in Computer Science (1998), Master in Computer Science (1995), both from University of Copenhagen Affiliations: Pioneer AI section, Applied Geometry Lab, and Faculty of Science External Roles: Visiting professor at McGill University (2012-13), co-founder of DigiCorpus Aps (2012-16) His research integrates scale-space theory, statistical shape analysis, and advanced imaging techniques for applications in medical diagnostics, materials science, and neuroscience. Recent work focuses on 3D reconstruction, persistent homology for bias correction, and AI-driven biomedical analysis. Jon teaches computer science at all academic levels, currently offering courses in bioimaging, signal processing, and deep learning. He emphasizes collaborative projects with external partners and has held administrative roles including Vice-Chair for Research at DIKU. His 15 most recent publications reflect expertise in medical imaging, 3D modeling, and AI applications, with subfields spanning neurodegenerative disease analysis, mitochondrial ultrastructure, and multi-scale image processing. Articles demonstrate interdisciplinary impact across medicine, biology, and materials science.

• Robotics
• Agricultural Robotics
• 3D Imaging
• +۶ مورد دیگر

Dr. Alen Alempijevic is the Deputy Head of School (Teaching and Learning) at the School of Mechanical and Mechatronic Engineering, University of Technology Sydney (UTS). He holds the academic rank of Senior Lecturer and coordinates Mechatronic Engineering programs. His research focuses on robotic perception, multi-modal sensor fusion, and AI applications in physical systems, with industry-driven projects in livestock monitoring, critical infrastructure, and autonomous systems. He completed his PhD in Robotics at UTS and contributed to the DARPA Urban Grand Challenge with the Sydney-Berkeley team. Education: PhD in Robotics (2004-2008), B.Eng (Computer Systems) with First Class Honors (2000-2003), B.E and B.Sc in Computer Science and Engineering from University of Belgrade (1995-1999). Research Interests: Livestock monitoring via 3D imaging, autonomous vehicles, sensor fusion, and robotics perception. His work includes developing technologies for cattle trait estimation, crowd dynamics prediction, and industrial automation. Funded Research: Notable grants include UTS Wool Bioharvesting (2024-2027), Objective real-time live cattle assessments (2020-2023), and Advanced livestock measurement technologies (2017-2018).

Zorah Lähnerمشاهده پروفایل

استاد

• Computer Vision
• Shape Matching
• Machine Learning
• +۳ مورد دیگر

Prof. Dr. Zorah Lähner is a Professor at the University of Siegen, leading research in the Department of Computer Vision. She will be transitioning to an Assistant Professor position at the University of Bonn starting January 2025. Her work bridges computer vision, machine learning, and quantum computing, focusing on fundamental geometric and algorithmic challenges in 3D shape analysis. Research interests span: Advanced shape matching methodologies Neural field representations on manifolds Quantum annealing applications in computer vision Scale-invariant correspondence frameworks Latent space alignment techniques Her publications demonstrate consistent innovation in geometric deep learning, with recent works exploring quantum-hybrid approaches for shape matching and neural fields for manifold learning. Publications predominantly appear in top-tier venues like CVPR, ICCV, and NeurIPS. While no specific awards are listed in the provided text, she maintains active collaborations across European institutions and supervises research in computer graphics and vision through her Lehrstuhl position.

• Computer Graphics
• Computer Vision
• Video Processing
• +۴ مورد دیگر

Prof. Dr. Thorsten Thormählen is a University Professor for Computer Graphics and Multimedia Programming in the Department of Mathematics and Computer Science at Philipps University Marburg, Germany, a position he has held since October 2012. Prior to this, he served as Substitute Professor for Interactive Graphics Systems at the University of Tübingen (2011-2012) and led the independent research group "Image-based 3D Scene Analysis" at the Max Planck Center for Visual Computing and Communication (2007-2012). His academic background includes a PhD (Dr.-Ing.) from the University of Hannover (2000-2005), where he also worked as a full-time scientific assistant, and a Diploma in Electrical Engineering from the University of Duisburg (1994-1999). Prof. Thormählen's research centers on Visual Computing , spanning Computer Graphics , Computer Vision , Video Processing , and Human-Computer Interaction . His work pioneers tools for 3D reconstruction (e.g., Multi-View Photometric Stereo), video manipulation (e.g., MovieReshape), and multimedia processing (e.g., GSN Composer), with groundbreaking contributions to accessibility through haptic and auditory interfaces for blind 3D modelers. His lab develops practical systems that bridge theoretical computer vision with real-world applications. Analysis of his 15 most recent publications reveals a consistent focus on photometric stereo techniques for 3D reconstruction, video processing innovations, and accessibility-driven interfaces. His work increasingly emphasizes inclusive design, particularly for visually impaired users, while maintaining technical rigor in camera calibration, surface modeling, and multi-sensor fusion. At the Max Planck Center, he established and led the "Image-based 3D Scene Analysis" research group, which advanced methods for reconstructing 3D environments from video sequences. His current work at Marburg continues this trajectory, integrating computer vision, graphics, and human-centered design to solve complex problems in digital content creation and accessibility.

Antonio Agudo Martínezمشاهده پروفایل

پژوهشگر

• Computer Vision
• Robotics
• Non-Rigid Structure from Motion
• +۳ مورد دیگر

Antonio Agudo Martínez is a Research Scientist at the Institut de Robòtica i Informàtica Industrial (IRI), a joint center of the Spanish National Research Council (CSIC) and Polytechnic University of Catalonia (UPC). His work spans computer vision, robotics, and machine learning with applications in medical rehabilitation, sports analytics, and renewable energy systems. He holds advanced degrees in Industrial Engineering, Computer Science, and a PhD in Computer Vision and Robotics from the University of Zaragoza. His research focuses on non-rigid structure from motion , 3D reconstruction , and deformation analysis , with significant contributions to medical applications (stroke rehabilitation), sports analytics (soccer trajectory modeling), and industrial systems (wind turbine monitoring). His publication record shows consistent high-impact output at top venues like CVPR, ICCV, and ECCV, with recent work emphasizing uncertainty quantification in diffusion models and multi-agent trajectory prediction. Notable scientific recognition includes a Best Paper Award Honorable Mention at ECCV 2018 for GANimation: One-Shot Anatomically Consistent Facial Animation. His research portfolio includes leadership of national projects like GreenVAR (renewable energy systems) and GRAvatar (realistic avatar generation), alongside contributions to SMARTGAZE II for low-vision mobility assistance. Dr. Agudo actively supervises doctoral research in computer vision applications, with current PhD candidates focusing on multimodal tracking for autonomous vehicles, soccer video understanding, sports metrics, and avatar generation. His international collaborations include work at Harvard University, Queen Mary University of London, University College London, Bordeaux University, and National University of Entre Ríos.

• 3D Shape Analysis
• Graph-Based Machine Learning
• Computer Vision
• +۴ مورد دیگر

Andrea Torsello is a researcher at the University of York, specializing in 3D shape analysis, graph-based machine learning, and quantum computing applications in computer vision. His work bridges theoretical and applied domains, focusing on pattern recognition, network thermodynamics, and remote sensing. PhD from University of York (2004) Published extensively in journals like IEEE Transactions and Pattern Recognition Research interests include: Quantum-inspired graph analysis 3D reconstruction techniques Manifold learning for complex networks Thermodynamic modeling of time-evolving systems Key contributions involve: Quantum walk-based graph similarity measures k-Anonymity for graph data Physics-driven CNN models for ocean wave reconstruction Game-theoretic approaches to shape matching

• Biomedical Engineering
• Cryoelectron Microscopy
• Magnetic Resonance Imaging
• +۷ مورد دیگر

Dr. Hemant D. Tagare serves as Professor of Radiology and Biomedical Imaging and of Biomedical Engineering at Yale School of Medicine. He maintains a primary appointment in Radiology & Biomedical Imaging and secondary appointment in Statistics, with extensive affiliations across Yale's research ecosystem including the Bioimaging Sciences Center, Center for Brain & Mind Health, Computational Biology and Biomedical Informatics, Image Processing & Analysis Group, and Yale Biomedical Imaging Institute. With a PhD from Rice University (1989), Dr. Tagare's research program addresses fundamental challenges in biomedical image analysis across four core areas: image segmentation (particularly cardiac ultrasound and brain MRI), non-rigid registration (developing axiomatic frameworks for brain deformation analysis), 3D protein structure reconstruction from Cryogenic Electron Microscopy, and shape theory (exploring topology and geometry of affine shape spaces). His work integrates machine learning and advanced numerical optimization techniques to develop innovative methodologies that advance medical imaging capabilities. Dr. Tagare's recent publications demonstrate continued productivity in cryo-EM particle picking consensus methods, MRI standardization techniques, perfusion measurement in vascular disease, and parameter mapping algorithms. His research program, supported by NIH funding, consistently bridges theoretical developments with practical clinical applications across biomedical imaging domains. Honors: Best poster award for "Tunnelling Descent: A New Algorithm for Active Contour Segmentation of Ultrasound Images" (2003) Francois Erbsmann Award (Honorable Mention) for outstanding paper in medical image processing (1993) National Science Talent Search Scholarship from Government of India (1977) Dr. Tagare maintains active collaborations with Yale researchers including Gigi Galiana, Dana Peters, Mark Gerstein, Pradeep Uchil, Todd Constable, and Walther Mothes. His work spans computational biology, medical physics, and clinical applications, demonstrating the interdisciplinary nature of modern biomedical imaging research that bridges engineering principles with clinical medicine.

Edith Tretschkمشاهده پروفایل

پژوهشگر

• Computer Graphics
• Computer Vision
• Machine Learning
• +۵ مورد دیگر

Edith Tretschk is a Research Scientist at Meta Reality Labs Research in the San Francisco Bay Area. She completed her Ph.D. in Computer Science at Saarland University and Max Planck Institute for Informatics (2018-2023), advised by Christian Theobalt . Her work bridges computer graphics , computer vision , and machine learning , with a focus on 3D reconstruction and quantum computing applications. Education Ph.D. in Computer Science (2018-2023), Max Planck Institute for Informatics & Saarland University M.Sc. in Computer Science (2017-2023), Graduate School of Computer Science, Saarland University B.Sc. in Computer Science (2014-2017), Saarland University Research Focus Her research explores 3D reconstruction of dynamic scenes, neural rendering , and quantum computing for vision tasks. Recent work includes time-consistent scene flow (SceNeRFlow), quantum auto-encoders (3D-QAE), and physics-driven template matching (φ-SfT). Article Trends Her publications span 3D vision , quantum algorithms , and neural scene modeling . Key themes include non-rigid deformation, quantum-hybrid approaches, and physics-based reconstruction. Scientific Recognition Bachelor Award (2017) for top CS graduates Deutschlandstipendium scholarship (2015-2017) NeurIPS Top Reviewer (2022) Additional Contributions She has delivered invited talks at World Labs, Meta, Nvidia, and Epic Games. Active as a reviewer for CVPR, ECCV, ICCV, and NeurIPS, she has also contributed to open-source projects and datasets.

Albert Wiltscheمشاهده پروفایل

استادیار

• Geometric Applications in Architecture
• Parametric Modeling
• Digital Fabrication
• +۳ مورد دیگر

Albert Wiltsche is an Assistant Professor at the Institute of Architecture and Media , Graz University of Technology. His academic journey began with studies in descriptive geometry and mathematics at Graz University of Technology and Karl-Franzens University of Graz, followed by a doctorate in 2000 with a dissertation titled "Interpolation of Points of a Regular Triangular Grid." He has been actively involved in teaching and research since 1994, transitioning from a contract assistant at the Institute of Geometry to his current role since 2007. Education: Graz University of Technology (PhD in Geometry, 2000), Karl-Franzens University of Graz (Mathematics), Graz University of Technology (Descriptive Geometry). Research Focus: Geometric applications in architecture, parametric modeling, digital fabrication, folding structures, and free-form surface discretization. His work explores the intersection of mathematical precision and architectural creativity, particularly in non-standard geometries and sustainable systems. Collaborations: Frequently works with Milena Stavric on projects like "Parametric Kirigami" and "Interactive Spots," integrating digital tools into architectural education and practice. Projects: Led FWF-funded research on "Non-standard Architecture with Ornaments and Planar Elements," emphasizing material efficiency and aesthetic control in curved surfaces. Publications: Over 84 research outputs spanning computational geometry, digital fabrication strategies, and pedagogical innovations in architectural education.

• Visual Computing
• Computer Vision
• Image and Video Processing
• +۵ مورد دیگر

Martin Eisemann is Professor of Computer Science and Director at the Computer Graphics Lab within the Computer Science Department of the College of Engineering at Technical University of Braunschweig. Previously, he served as full professor for Computer Graphics at TH Köln (2015-2020) where he co-founded and led the Advanced Media Institute. His academic journey includes a Diploma (2006) from University of Koblenz-Landau and PhD (2011) from TU Braunschweig, followed by post-graduate work at TU Delft. His research spans visual computing with emphasis on computer vision, image/video processing, computer graphics, ray tracing, Monte-Carlo simulations, information visualization, and visual analytics. Recent work demonstrates strong focus on neural rendering techniques including neural point clouds, Gaussian splatting, and holography applications, reflecting evolving trends toward AI-integrated graphics pipelines and immersive visualization systems. His publications consistently address real-time performance challenges while advancing visual quality metrics. VMV'16 Best Paper Award EGSR'16 Best Paper Award ACM Multimedia 2015 Best Student Paper Award Graphics Interface 2015 Best Student Paper Award SAP 2025 Best Student Paper Honorable Mention As Dean of Studies (2023-2027) and former Audit Committee member, he actively shapes academic policy. His community service includes program committee roles for SAP, WACV, and Computational Visual Media conferences. Current research includes a planned sabbatical (April-October 2025) focusing on visual computing challenges. The Computer Graphics Lab maintains active collaborations with DLR, Ford, and European institutions through projects spanning planetary visualization, video conferencing security, and ADHD cognitive support tools.

• Control Systems
• Machine Learning
• Optimization Algorithms
• +۳ مورد دیگر

Pedro Manuel Quintas Aguiar is an Associate Professor at the Department of Electrical and Computer Engineering, Instituto Superior Técnico (University of Lisbon), specializing in Systems, Decision, and Control. His work integrates optimization, machine learning, and computer vision with applications in distributed systems, 3D reconstruction, and robotics. He leads research in structured prediction and distributed algorithms for sensor networks. Education: PhD in Electrical Engineering (assumed based on role) Not explicitly stated but inferred from academic rank Research Interests: Optimization algorithms for distributed systems Machine learning for computer vision (attention mechanisms, shape representation) 3D reconstruction from video and motion estimation Robotic perception and bin-picking applications His recent work emphasizes scalable distributed optimization (e.g., D-ADMM algorithms) and robust visual attention models. Grants & Labs: Collaborations on sensor networks and underwater communications Focus on real-time systems and low-light video processing Labs/Teams: Involved with ISR (Institute for Systems and Robotics) at IST.

• Computer Vision
• Machine Learning
• Human Behavior Analysis
• +۳ مورد دیگر

Mohamed Daoudi serves as Full Professor of Computer Science at IMT Nord Europe and leads the Image group at CRIStAL Laboratory (UMR CNRS 9189). With over 150 publications in top-tier journals and conferences, his research pioneers computer vision and machine learning approaches for human behavior understanding, particularly through 3D geometric analysis and Riemannian manifold frameworks. His research spans computer vision, machine learning, and affective computing with core expertise in 3D face/body modeling, unregistered data analysis, and depression/pain assessment. Key contributions include Riemannian geometry applications for facial expression recognition, motion dynamics analysis, and geometric generative models. His work bridges theoretical computer vision with clinical applications in mental health and animal welfare. Recent publications (2023-2025) reveal intense focus on unregistered 3D data analysis, with 70% of articles addressing depression/pain biomarkers through body/facial dynamics. Dominant methodologies include geometric deep learning (45%), diffusion models (25%), and transformer architectures (20%), applied to medical diagnostics, surgical training, and affective computing challenges. Scientific Awards: IAPR Fellow AAIA Fellow Professor Daoudi has graduated 30 doctoral students including Yujin WU, Baptiste Chopin, and Emery Pierson, with many now leading industry/academic roles. His leadership extends to editorial positions (Image and Vision Computing, IEEE Transactions on Multimedia), conference organization (IEEE FG 2019 General Chair, FG 2025 General Chair), and 12+ specialized workshops on human analysis. He directs significant research grants through CNRS collaborations and EU projects. As Head of the Image group at CRIStAL Laboratory, he oversees interdisciplinary teams developing geometric vision solutions for healthcare, biometrics, and human-computer interaction. Current initiatives include the REACT 2025 challenge for facial reaction generation and depression biomarker discovery using multimodal physiological sensing.