جست‌وجوی استاد و پژوهشگر

• Solar Physics
• Heliospheric Physics
• Coronal Mass Ejections (CMEs)
• +۳ مورد دیگر

Laura Balmaceda is a Research Assistant Professor in the Physics & Astronomy Department, focusing on solar and heliospheric phenomena. Her work primarily involves analyzing coronal mass ejections (CMEs), solar energetic particles (SEPs), and interplanetary shock dynamics using multi-spacecraft observations from missions like Solar Orbiter, Parker Solar Probe, and STEREO. She contributes to instrumentation development, including calibration and data analysis for coronagraphs like CCOR and WISPR. Her research bridges observational data with theoretical models to understand particle acceleration mechanisms, CME propagation, and the evolution of magnetic structures in the corona and heliosphere. Key topics include magnetic flux rope stability, SEP longitudinal distribution, and the role of ICME-driven shocks in energetic particle events. She collaborates extensively with international teams to leverage multi-point observations for comprehensive solar system studies. Dr. Balmaceda has co-authored over 80 peer-reviewed articles since 2017, with a focus on solar wind structures, CME kinematics, and space weather forecasting. Her work emphasizes improving CME reconstruction techniques and quantifying uncertainties in heliospheric models. She actively participates in instrument calibration and mission planning for cutting-edge coronagraphs, ensuring robust data interpretation for future solar missions. Her contributions span from low-corona CME dynamics to interplanetary particle transport, with applications to both fundamental science and practical space weather predictions.

Aritra Duttaمشاهده پروفایل

استادیار

• Machine Learning
• Federated Learning
• Optimization
• +۷ مورد دیگر

Aritra Dutta is an Assistant Professor at the AI Initiative of the University of Central Florida (UCF), primarily affiliated with the Department of Mathematics and secondarily with the Department of Computer Science. He also holds an affiliation with the Pioneer Centre for AI (P1), Denmark. His research focuses on optimization (stochastic/nonconvex), distributed computing (including federated learning), numerical linear algebra, machine learning, low-rank approximation, and computer vision applications such as image/video analysis and object detection/tracking. Dr. Dutta’s work emphasizes interdisciplinary approaches, blending mathematical rigor with computational efficiency. He actively seeks Ph.D. students and postdocs with strong foundations in mathematics (optimization, linear algebra) or computer science (ML, distributed systems), prioritizing candidates with publication records in top-tier venues. His teaching includes courses in applied mathematics and computational methods. His research outputs span communication-efficient distributed learning frameworks, convergence analysis of optimization algorithms, and vision transformer architectures. Notable projects include GAEA (geolocation-aware conversational models) and MAVREC (multi-view aerial visual recognition). Postdoc opportunities: Open for exceptional candidates. Labs/Initiatives: UCF AI Initiative (UCF Aii), UCF Center for Research in Computer Vision (CRCV). Grants: Competitive research assistantships with tuition support.

Miles Hansardمشاهده پروفایل

مدرس ارشد

• Computer Vision
• 3D Scene Reconstruction
• Robotics
• +۶ مورد دیگر

Dr. Miles Hansard is a Senior Lecturer at Queen Mary University of London's School of Electronic Engineering and Computer Science. His research focuses on 3D scene reconstruction, multi-view imaging, depth cameras, radar localization, and human vision. He specializes in geometric aspects of vision, image processing, and robotics applications. His teaching includes modules on Computer Graphics (for both postgraduate and undergraduate students) and Introduction to Multimedia Systems. These courses cover topics like 3D graphics algorithms, human perception of color, and multimedia system fundamentals. Dr. Hansard's work integrates sensor technologies such as time-of-flight cameras and millimeter-wave radar to improve 3D reconstruction and robotic systems. He contributes to projects like the GRIP software framework for robotic grasping and has published extensively in journals like IEEE Transactions on Image Processing and the International Journal of Neural Systems. He is affiliated with the Centre for Multimodal AI, where he collaborates on research involving sensor fusion, autonomous systems, and visual perception. His expertise bridges computer vision, robotics, and multimedia engineering.

• Machine Learning
• Computer Vision
• Image Processing
• +۳ مورد دیگر

Matthias O. Franz is a Professor in the Department of Computer Science at Hochschule Konstanz University of Applied Sciences, Konstanz, Germany, since 2007. His academic work spans theoretical and applied research in Machine Learning, Computer Vision, and Computational Neuroscience. Research Interests His research focuses on interdisciplinary applications of computational methods, including: Machine Learning algorithms for image analysis and signal processing Computer Vision techniques in object recognition and 3D reconstruction Computational Neuroscience studies on echolocation and visual saliency Quantum Physics applications in space missions Notable contributions include kernel methods for image modeling, steganalysis frameworks, and biomimetic navigation systems inspired by biological processes. Publication Trends Dr. Franz’s 15 most recent publications (2022–2011) demonstrate a trajectory from foundational work in nonlinear system modeling to applications in space technology, computer vision, and acoustic signal analysis. Key trends include: 2022: Image novelty detection using mean-shift algorithms for sensor technology 2015: Dual-species atom interferometry for space-based physics and hybrid image registration 2014: Geometric primitive classification in point clouds and multi-camera stereo matching 2013–2011: Steganalysis, Gaussian process calibration, and computational models of echolocation 2008–2007: Early work on Wiener series and visual saliency prediction

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.

• Remote Sensing
• Photogrammetry
• Civil Engineering
• +۹ مورد دیگر

Dr. Maria-Valasia Peppa is a researcher at Newcastle University's School of Civil Engineering and Geosciences . Her work focuses on remote sensing, photogrammetry, and geospatial technologies, with applications in hydrodynamic modeling, landslide monitoring, and urban infrastructure analysis. Key Research Areas: UAV-based photogrammetry, glacial lake dynamics, digital elevation models (DEMs), and environmental data uncertainty. Recent Trends: Integration of deep learning with CCTV for traffic analysis, calibration of multisensor UAV systems, and real-time flood nowcasting frameworks. Collaborations: Active partnerships with Professors Jon Mills, Claire Walsh, and international institutions in Africa and Nepal. Applications: Cultural heritage mapping, water security strategies, and urban air quality modeling.

Andreas Nüchterمشاهده پروفایل

استاد

• Robotics
• Computer Vision
• Sensor Fusion
• +۵ مورد دیگر

Andreas Nüchter is a Professor and Chair of Robotics at Julius-Maximilians-University Würzburg (Germany), leading the Chair of Computer Science XVII. He holds additional roles including Visiting Chair at ENSTA - Institut Polytechnique de Paris, Dean of Studies at the Institute of Computer Science, and Vice President of Zentrum für Telematik e.V. His research focuses on robotics, 3D reconstruction, SLAM, and sensor systems for autonomous systems. He has authored influential papers in IEEE Transactions on Robotics, Acta Astronautica, and robotics conferences like ICRA and IROS. Education: Not explicitly detailed in text, but inferred through academic roles. Research Interests: Robotics, computer vision, sensor fusion, autonomous systems, 3D reconstruction, and space robotics applications. His work emphasizes real-time systems, planetary exploration, and open-source software frameworks like SceneFactory and libBICOS. Recent projects include CNN-based spacecraft pose estimation, spherical mobile mapping systems, and radar SLAM (RIV-SLAM). Advising & Grants: Mentors a team including MSc/BSc students (e.g., Luca Anteunis, Fabian Arzberger). Involved in grants related to robotics, mining automation (AMADEE-24), and space exploration. Collaborates with institutions like NASA (CADRE lunar rovers) and Fraunhofer IPM. Labs/Teams: Leads the Robotics Lab at JMU, develops spherical robots for planetary missions, and maintains open-source libraries (libBICOS, SceneFactory). Active in projects like AMADEE-24 Mars simulation for human-robot interaction.

• Computer Vision
• 3D Reconstruction
• Neural Networks
• +۳ مورد دیگر

Fangjinhua Wang is a Researcher affiliated with the Department of Computer Science at ETH Zurich, working within the Professorship for Computer Science. Their role involves contributing to cutting-edge research in fields such as 3D reconstruction, computer vision, and neural networks. The research focuses on advancing methodologies like scene graph manipulation, multi-view stereo techniques, and holistic human-scene reconstruction. Collaborations and projects emphasize practical applications in robotics, computer graphics, and AI-driven systems. While no explicit education details are provided, the research trajectory reflects a deep engagement with computational methods for 3D modeling and vision-based systems. The work bridges theoretical advancements with real-world applications, addressing challenges in scene understanding, object interaction, and human-robot collaboration. Research interests are centered on interdisciplinary topics including neural representation learning, robust visual localization, and the integration of geometric priors for high-fidelity reconstructions. The output demonstrates a commitment to both foundational research and applied solutions in computer science and robotics.

Chao Zhangمشاهده پروفایل

دانشیار

• Dielectrics
• Electrochemistry
• Electrolyte materials
• +۳ مورد دیگر

Chao Zhang is an Associate Professor at the Department of Chemistry-Ångström Laboratory, Uppsala University, specializing in computational electrochemistry and multi-scale modeling of electrolyte materials. His research bridges atomistic simulations with machine learning approaches to address challenges in energy storage and conversion systems. Education: Dr. rer. nat. from RWTH Aachen University (2013); Docent from Uppsala University (2020) Appointments: Postdoctoral researcher at the University of Cambridge (prior to joining Uppsala in 2017) His group develops finite-field methods for computational electrochemistry and investigates electrified solid-liquid interfaces. Recent research trends include neural rendering for underwater SLAM systems (2025), robust path-following control in marine robotics, and event-based localization in LiDAR-integrated environments. Scientific Awards: ERC Starting Grant (2020) Junior Research Fellowship, Wolfson College (2015) Jülich Excellence Prize for Young Scientists (2013)

Norbert Haalaمشاهده پروفایل

استاد مدعو

• Computer Vision
• Geoinformatics
• 3D Data Reconstruction
• +۵ مورد دیگر

Norbert Haala is an Adjunct Professor and Deputy Director at the University of Stuttgart's Department of Photogrammetric Computer Vision. He leads the Research Group in Photogrammetric Computer Vision and is involved in ISPRS Working Group II/2 (Point Cloud Generation) and EuroSDR Commission 2 (Modelling and Processing). His work focuses on 3D data collection, SLAM algorithms, LiDAR integration, and UAV-based geospatial technologies. Research interests include image-based data collection, photogrammetric computer vision, and semantic segmentation of 3D point clouds. He has contributed to benchmarks like Hessigheim 3D and TIME, and developed tools like SURE for dense image matching. Teaching includes courses on digital image processing, terrain modeling, and computer vision. His publications emphasize real-time mapping, hybrid georeferencing, and neural surface reconstruction from airborne imagery. Projects involve UAV monitoring, indoor SLAM for robotics, and multi-modal data fusion for urban modeling. He collaborates on EuroSDR initiatives and publishes regularly in remote sensing and robotics domains.

Marco Volinoمشاهده پروفایل

مدرس ارشد

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

Marco Volino is a Senior Lecturer in Computer Vision and Graphics at the University of Surrey's Centre for Vision, Speech and Signal Processing (CVSSP). He holds a PhD and MEng in Electronic Engineering from the University of Surrey. His research focuses on advancing visual media production through interdisciplinary work in computer vision, graphics, and machine learning, with applications in film, broadcast, gaming, and immersive technologies like AR/VR. He has led projects such as the Polymersive and ALIVE initiatives, and developed hardware/software systems for volumetric video and photogrammetry. Volino has secured funding including an Epic MegaGrant and InnovateUK projects, and serves on the editorial boards of multiple conferences. Education: PhD Computer Vision and Graphics (2016, University of Surrey), MEng Electronic Engineering (2011, University of Surrey), BTec National Diploma in Electrical/Electronic Engineering (2006). Professional experience includes roles at BBC R&D, USC Institute for Creative Technologies, and Sony Broadcast Labs. He teaches modules like AR/VR and the Metaverse, and supervises MSc and PhD students in topics such as volumetric capture and digital humans. Research Highlights: Volumetric video compression, 3D human reconstruction, real-time motion capture, and immersive media production. Key Contributions: Developed 64-camera photogrammetry systems, WebGL-based renderers, and tools for Unreal Engine integration. Leadership: Co-chair of European Conference on Visual Media Production (CVMP) 2023-2024 and Area Chair for BMVC 2021-2024.

Boris Jutziمشاهده پروفایل

استاد

• Active Optical Sensors
• Computer Vision
• Laser Scanning
• +۷ مورد دیگر

Prof. Dr. Boris Jutzi is a leading academic in photogrammetry and remote sensing, currently serving as Professor at Karlsruhe Institute of Technology (KIT) and acting head of the Chair of Photogrammetry and Remote Sensing at Technical University of Munich (TUM). His research focuses on active optical sensors, computer vision, laser scanning, and 3D reconstruction techniques. He holds a diploma in electrical engineering from University of Kaiserslautern, a PhD from TUM, and venia legendi from KIT. Affiliations: KIT Institute of Photogrammetry and Remote Sensing, TUM Chair of Photogrammetry and Remote Sensing Education: Diploma in Electrical Engineering (University of Kaiserslautern) Doctorate (TUM) Venia Legendi (KIT) His research interests include: Neural Radiance Fields (NeRF) for 3D reconstruction LiDAR technology and applications UAV-based remote sensing Geospatial data fusion Computer vision in environmental monitoring Awards: Faculty Teaching Award (2020) Best Paper Awards (2019, 2016, 2014, 2006) His work emphasizes novel sensor integration and automated scene analysis , with contributions to urban and environmental 3D modeling. Current projects include underwater scene reconstruction via NeRFs and large-scale digital twin datasets (e.g., TUM2TWIN).

Bastian Goldlückeمشاهده پروفایل

دانشیار

• Computer Vision
• Variational Methods
• Light Field Analysis
• +۳ مورد دیگر

Bastian Goldlücke serves as an Associate Professor in the Department of Computer Science at the University of Konstanz since 2014. His academic journey includes postdoctoral positions at the University of Heidelberg (2011), TU Munich (2010), and the University of Bonn (2009), following a Ph.D. from the Max Planck Institute for Computer Science in Saarbrücken (2006). His research centers on variational methods and their applications in computer vision, with specialized focus on light field analysis and inverse problems . Key contributions include novel frameworks for light field decomposition, real-time 3D reconstruction, and attention-based neural representations. His work bridges mathematical optimization with practical computer vision challenges in autonomous systems and 3D imaging. Notable scientific recognition includes: ERC Starting Grant 'Light Field Imaging and Analysis' (2013) Funding through SFB Transregio 'Quantitative Methods for Visual Computing' Prof. Goldlücke actively contributes to the academic community as a reviewer for major conferences and journals, co-organizer of the 'Light Fields for Computer Vision' workshops at ECCV 2014 and CVPR 2017, and area chair for ACCV 2014 and 3DV 2016. His current research is supported by significant European and German research grants focusing on computational imaging and visual analysis.

• 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.

Jianfei Caiمشاهده پروفایل

استاد

• Computer Vision
• Multimedia
• Visual Computing
• +۵ مورد دیگر

Roles and Affiliations: Jianfei Cai is a Professor at Monash University's Faculty of IT, leading the Department of Data Science & AI. Previously, he held roles including Head of the Data Science & AI Department, and was a Full Professor at NTU's School of Computer Science and Engineering. He is a co-recipient of multiple paper awards and an IEEE Fellow. Currently serves as General Chair for ACM Multimedia 2024 and on editorial boards of TPAMI and IJCV. Education: PhD in Electrical Engineering, University of Missouri Columbia (2002) MEng in Electrical Engineering, Southeast University (1997) BEng in Electrical Engineering, Nanjing University of Aeronautics and Astronautics (1994) Research Interests: Focuses on computer vision, deep learning, vision-language systems, 3D imaging, and medical imaging applications. His work spans generative AI, neural scene representation (e.g., Gaussian Splatting), and open-vocabulary semantic segmentation. He has published over 380 papers and led projects in trustworthy AI and 3D vision. Key Contributions: Developed MVSplat (3D Gaussian Splatting from sparse views) Pioneered open-vocabulary object detection via scene graph discovery Advanced diffusion models for multi-sensor fusion and panorama synthesis Awards and Recognition: Monash FIT Dean's Researcher of the Year Award IEEE Fellow ACCV/ICCM/IEEE ICIP paper awards Recipient of Google/Adobe research gifts Grants and Labs: Leading projects on trustworthy generative AI, 3D Gaussian splatting compression, and safe AI Former director of NTU's Data Science & AI Research Center