Dr. Marcel Köster is a researcher affiliated with the Ubiquitous Media Technology Lab at the German Research Center for Artificial Intelligence (DFKI) and the Saarland Informatics Campus. His work focuses on GPGPU computing, particle simulations, compilers, and optimization techniques. Email: Marcel.Koester@dfki.de Phone: +49 681 85775 7750 Location: Gebäude D3 1, Room 0.13, Saarbrücken Research Interests Dr. Köster's research integrates GPU computing with simulation algorithms and compiler optimization. He contributes to advancements in parallel processing, domain-specific languages, and scientific visualization through both theoretical exploration and practical implementations. His publications highlight innovative applications of GPU acceleration to heuristic optimization, state generation, and particle simulations. These works demonstrate expertise in thread compaction, shared memory utilization, and warp scheduling. Teaching Experience Dr. Köster has taught multiple courses at HBK Saar, including: Artificial Intelligence (Summer 2019) Grundlagen der Medieninformatik (Winter 2016/17) Physical Simulations on Media Facades (Winter 2015/16) Core Lecture: Compiler Construction (Winter 2013/2014)
Kai Han is an Assistant Professor at The University of Hong Kong's School of Computing and Data Science, where he directs the Visual AI Lab. His research focuses on computer vision, machine learning, and artificial intelligence with specific interests in open-world learning, 3D vision, generative AI, and foundation models. He aims to achieve principled visual understanding and build reliable AI systems that close the intelligence gap between machines and humans. Dr. Han's research interests span multiple areas in visual AI, with particular emphasis on developing methods for open-world visual understanding. His work addresses fundamental challenges in category discovery, visual correspondence, 3D reconstruction, and generative modeling. He has made significant contributions to novel category discovery, open-set recognition, and visual correspondence problems, with his AutoNovel framework being particularly influential in the field. His current research explores the intersection of generative models and visual understanding, particularly focusing on how foundation models can be leveraged for comprehensive visual analysis. His publication record demonstrates a clear evolution from traditional computer vision problems toward more challenging open-world scenarios and generative approaches. Early work focused on 3D reconstruction of transparent and mirror surfaces, while more recent publications explore category discovery, visual correspondence, and generative AI. The trend shows increasing focus on foundation models, large language model integration with vision systems, and creating more robust visual understanding systems that can handle real-world open-set scenarios. Best Paper Runner-Up Award at CVPR Workshop on Continual Learning in Computer Vision, 2022 Outstanding Reviewer for ICCV 2021 (top 5%) Outstanding Reviewer for CVPR 2021 Outstanding Reviewer for CVPR 2020 Travel Award, ICLR 2020 Doctoral Consortium Travel Grant, ICCV 2017 Dr. Han actively mentors PhD students and postdocs, with numerous students appearing as first authors on his publications. His lab has secured multiple funding opportunities including HKU-PS, HKPFS, PGS, HKU-BICI, and HKU-ASTRI scholarships. He serves as Area Chair for major conferences including CVPR 2026, ICLR 2026, and AAAI 2026, demonstrating his standing in the research community. His lab, the Visual AI Lab, focuses on creating robust visual understanding systems that can handle real-world scenarios beyond closed-set recognition.
Michal Španěl is an Associate Professor in the Department of Computer Graphics and Multimedia at the Faculty of Information Technology, Brno University of Technology. His academic work centers on visual computing with emphasis on practical implementations and system architectures. His research spans Computer Graphics , Virtual Reality , and 3D Visualization , focusing on real-time rendering techniques, scientific visualization frameworks, and multimedia system design. Key methodologies include GPU programming, interactive visualization pipelines, and cross-platform graphics applications. Dr. Španěl maintains active scholarly identifiers including ORCID iD 0000-0003-0193-684X, ResearcherID G-9639-2016, and Scopus Author ID 22836945200 for tracking his academic contributions.
Mårten Sjöström is a Professor in Signal Processing at Mid Sweden University, where he serves as the highest representative of the research subject Computer and System Sciences and is part of the managerial group of the Department of Information and Communication Systems (IKS). He leads the Realistic 3D research group and has extensive experience in both academic and industrial settings. His educational background includes a Master of Science from Linköping University (Applied Physics and Electrical Engineering, 1992), a Technical Licentiate degree from the Royal Institute of Technology, Stockholm (Signal Processing, 1998), and a PhD from Ecole Polytechnique Federale de Lausanne (Modelling of Non-linear Systems, 2001). He obtained his Docent degree (Associate Professor) in 2008 and Professor's degree in Signal Processing in 2013. His primary research focuses on Multi-Dimensional Signal Processing with emphasis on System Modelling and Identification. He has successfully applied these techniques to Image and Video Processing, Multi-media Communications, and currently specializes in Multi-Scopic 3D and Light Field Technology including capture, processing, coding, and presentation/visualization. His work spans theoretical foundations to practical implementations across various application domains. His recent publication record demonstrates a clear trajectory toward advanced light field and 3D imaging technologies, with significant contributions to compression algorithms, depth estimation techniques, quality assessment metrics, and telepresence applications. His research bridges theoretical signal processing with practical industrial implementations, particularly in remote operation, mining applications, and immersive visualization systems. Best Paper Award at MMEDIA 2013 Quality Reviewer Award at ICME 2013 Professor Sjöström has supervised an extensive number of doctoral and licentiate students, with numerous current PhD candidates expected to complete their degrees in 2025. His teaching portfolio covers a wide range of subjects including Applied Signal Processing, Automatic Control, Computer Hardware and Architecture, and specialized PhD courses in Video Processing and Realistic 3D. He has led numerous research projects both current and completed, including IMMERSE, PLENOPTIMA, and various initiatives in 3D video technology and visualization. As founder and head of the Realistic 3D research group, he directs activities focused on synthesis and capture of 3D images and video, rendering techniques for virtual perspective views, system modeling for 3D capture and presentation, coding of 3D content, quality metrics and assessments, and remote control and measurement systems. The group maintains strong industrial collaborations across multiple sectors.
Raoul de Charette is a Research Director in computer vision at Inria Paris, leading the Astra-Vision group within the ASTRA team. His academic journey includes a PhD from Mines Paris (2012) and Habilitation (HDR) in 2022, with research stints at Carnegie Mellon University (2011), Mines Paris (2013), and the University of Makedonia (2014). His educational background comprises: PhD from Mines Paris (2012) Habilitation (HDR) (2022) De Charette's research centers on robust and interpretable visual scene understanding , spanning 3D scene reconstruction, domain adaptation, material recognition, and physics-grounded vision foundation models. His work integrates physical principles and synthetic data to enhance model robustness in real-world scenarios like autonomous driving and urban environments. Key contributions include uncertainty-aware 3D scene completion (PaSCo), material extraction from single images (Material Palette), and prompt-driven domain adaptation (PODA). Recent publications reveal a strategic shift toward vision-language integration, material-centric scene understanding, and foundation models that minimize labeled data dependency. His group pioneers physics-informed approaches to improve interpretability and resilience against environmental challenges like adverse weather conditions. Key scientific recognition includes: Best Paper Honorable Mention at EGSR 2025 for MatSwap ELLIS Membership PR[AI]RIE-PSAI Fellowship De Charette actively mentors four PhD students—Fatima Balde, Mohammad Fahes, Ivan Lopes, and Tetiana Martyniuk—often in industry collaborations with Valeo.ai and Kyutai. He secures funding through fellowships and industry partnerships, regularly opening PhD positions (including a 2025 opening for Physics-Grounded Vision Foundation Models). As an area chair for CVPR, ECCV, WACV, and IROS, he shapes the field through conference leadership and co-organizing initiatives like the African Computer Vision Summer School. He directs the Astra-Vision group within Inria Paris' ASTRA team, driving interdisciplinary research at the intersection of computer vision, machine learning, and physics-based modeling for real-world deployment in robotics and intelligent transportation systems.
Björn Ommer is a full Professor at Ludwig Maximilian University of Munich (LMU) where he heads the Computer Vision & Learning Group. Previously, he was a full professor at Heidelberg University and served as a director of the Interdisciplinary Center for Scientific Computing (IWR) and the Heidelberg Collaboratory for Image Processing (HCI). He is affiliated with multiple prestigious institutions including the Bavarian AI Council, ELLIS unit Munich, the Helmholtz Foundation, and the Munich Center for Machine Learning (MCML). Dr. Ommer received his PhD from ETH Zurich where he was awarded the ETH Medal for his dissertation 'Learning the Compositional Nature of Objects for Visual Recognition.' After completing his doctoral studies, he held a post-doctoral position in the Computer Vision Group of Jitendra Malik at UC Berkeley. His primary research interests span all aspects of semantic image and video understanding based on deep machine learning, with particular emphasis on generative approaches for visual synthesis (including Stable Diffusion), invertible deep models for explainable AI, deep metric and representation learning, and self-supervised learning paradigms. His work has significant interdisciplinary applications in digital humanities and neurosciences. His extensive publication record demonstrates a clear progression toward increasingly sophisticated generative models, culminating in the development of Stable Diffusion. His recent work focuses on improving diffusion models, exploring flow matching techniques, and developing more controllable generative systems with applications across multiple domains. German AI-Prize 2024 Technology-Prize of Eduard-Rhein-Foundation 2024 Nominated for German Future Prize of the President of Germany ELLIS Fellow ETH Medal for Dissertation Best Paper Award at CVPR'21 AI for Content Creation Workshop Professor Ommer serves as an associate editor for IEEE T-PAMI and has held significant leadership roles in major computer vision conferences including program chair for GCPR and Senior/Area Chair for CVPR, ICCV, ECCV, and NeurIPS. He delivered the opening keynote at NeurIPS'23 and has supervised numerous PhD students who have gone on to positions at leading technology companies including Amazon, Facebook, and Apple. His research group is located in downtown Munich and actively recruits talented students and researchers for cutting-edge work in computer vision and machine learning.
Togan Tong serves as Associate Professor in the Department of Building Information at Yıldız Technical University's Faculty of Architecture, where he has maintained continuous academic service since 1992. His expertise spans computational design methodologies and immersive technology applications within architectural practice and education. His educational foundation includes: Bachelor of Architecture from Yıldız University (1988) Master of Architecture in Building Science from Yıldız Technical University (1990) Ph.D. in Building Information from Istanbul Technical University (2000) Research initiatives focus on Architectural Computing , Building Information Modeling , and Immersive Technologies , with particular emphasis on human-computer interaction in design environments. Current projects explore VR/AR interfaces for architectural modeling, computational space planning algorithms, and game-based historical reconstruction systems. Publication analysis reveals a pronounced shift toward immersive educational applications since 2020, with significant contributions in VR ergonomics, spatial cognition studies, and BIM integration methodologies. His work bridges technical computing and architectural pedagogy through systematic reviews and empirical interface studies. Academic mentorship includes supervision of 9 theses across architectural computing disciplines. Professional activities extend to Digital Design Education Consultancy for the Istanbul Metropolitan Branch of the Chamber of Architects, influencing curriculum development at institutional levels. Operational activities center around the YTU Bot Group research collective, utilizing the university's digital design infrastructure for advanced visualization projects and computational prototyping in architectural contexts.
Ingrid Scholl is a Professor at the University of Applied Sciences Aachen , specializing in computer science education. She teaches modules including Algorithms and Data Structures , Computer Graphics , Image Processing , and Virtual Reality/Augmented Reality . Her interdisciplinary project DataLake - Big Data Analysis and Visualizations focuses on extracting insights from large datasets using VR/AR technologies. Key Research Areas : Artificial Intelligence, Autonomous Systems, Virtual Reality, Medical Imaging, and Parallel Programming. Projects : Development of low-energy sensors for environmental monitoring, digital twin modeling of buildings for VR visualization, and collaborative VR experiences via HTC Vive. Publications highlight her work on autonomous mining vehicles, scene generation for AI training, and volume rendering in VR. Her recent contributions focus on operational design domains and mapping approaches in autonomous systems.
Markus Wacker serves as Professor of Computer Graphics at the Faculty of Computer Science and Mathematics, Dresden University of Applied Sciences (HTW Dresden). His office is located in room Z348 with direct contact via +49 351 462 2684. His research focuses on visual computing disciplines requiring: Real-time rendering techniques 3D animation pipelines Interactive game systems Digital compositing workflows Media production methodologies Spatial visualization frameworks Professor Wacker teaches core modules across Media Informatics and Applied Computer Science programs including Computer Graphics/Visualization II, Advanced Computer Animation, and Interaction/Game Techniques for undergraduate and graduate students in semesters 2-7.
Dr. Jianhua Wu is a researcher affiliated with the Department of Computer Science at RWTH Aachen University , focusing on Computer Graphics and Mesh Processing . His work addresses challenges in 3D modeling, surface reconstruction, and digital watermarking. Department: Department of Computer Science, RWTH Aachen University. Email: wu@informatik.rwth-aachen.de Research Interests: Jianhua Wu’s research centers on Computer Graphics , with a focus on surface splatting , variational approximation , and spectral watermarking of 3D models. His methods improve robustness in geometric data processing and reduce computational complexity for large datasets. Publication Trends: His 2002–2005 work emphasizes mesh decimation , splatting algorithms , and digital watermarking , leveraging techniques like radial basis functions and multiple-choice optimization to enhance efficiency and accuracy. Scientific Awards: Best Student Paper Award, Eurographics Symposium on Point-Based Graphics 2005
Dr. Henrik Zimmer is a researcher at RWTH Aachen University specializing in computer graphics and geometry processing. His work bridges theoretical computational geometry with practical applications in digital fabrication, medical visualization, and industrial manufacturing. Affiliated with the Department of Computer Science, he has made significant contributions to mesh processing, 3D modeling, and optimization algorithms for real-world applications. His research focuses on geometry optimization for fabrication constraints, including Zometool-based approximation of freeform surfaces and rationalization of point-folding structures. Key interests include Mesh processing and topology preservation Variational methods for planar polygonal meshing Mixed-integer optimization for quadrangulation Medical visualization techniques for diffusion fiber tracking Industrial vision systems for laser welding process control His publication record shows consistent innovation from 2006 to 2014, with recent work emphasizing digital fabrication and practical optimization for consumer-level manufacturing. Notable scientific contributions include: Efficient algorithms for shortest path-concavity computation in 3D meshes Interactive volume-based visualization for diffusion MRI data Rationalization methods reducing fabrication costs by over 90% Novel approaches to melt pool monitoring in industrial welding Zimmer's collaborative work with Leif Kobbelt demonstrates strong industry-academia connections, particularly in translating geometric algorithms to manufacturing applications. His research spans both theoretical computer graphics (SIGGRAPH, Eurographics) and industrial applications (laser welding process control), reflecting a unique interdisciplinary approach. Current work focuses on making advanced geometric modeling accessible through personal fabrication technologies.
Marie-Paule Cani is a Professor of Computer Science at Ecole Polytechnique (IP Paris), where she serves as Dean of the Master of Science and Technology program. She is a member of the Académie des sciences and leads research in the LIX laboratory (CNRS/Ecole Polytechnique, IP Paris). Her career spans several prestigious institutions including Grenoble INP and Collège de France. Dr. Cani earned her M.Sc. in Computer Science from Ecole Normale Supérieure & University Paris XI in 1987, followed by a Ph.D. in Computer Graphics from University Paris XI in 1990 under advisor Claude Puech. She completed her Habilitation in Computer Science from Institut National Polytechnique de Grenoble in 1995. Professor Cani's research focuses on advancing user-centered, creative 3D modeling and animation systems. Her work aims to develop intelligent systems that help users express shapes in motion they have in mind, whether they are computer artists, engineers, or scientists from other disciplines. She pioneered methodologies that provide expressive, gesture-based control (such as sketching, deformation, copy-pasting) while augmenting graphical models with knowledge from priors or statistics learned from examples. Her research spans multiple areas including implicit surfaces, developable surfaces, procedural models, physically-based animation, and sketch-based modeling. Her recent publications demonstrate a continued focus on innovative approaches to 3D modeling, animation, and simulation. Her work bridges computer graphics with applications in geology, biology, and virtual environments. Recent trends show increasing integration of machine learning techniques with traditional graphics approaches, particularly in procedural modeling and animation control. ACM Siggraph Steven A. Coons Award (2023) Member of the ACM Siggraph Academy (2019) Member of Academia Europaea (2013) Silver medal from CNRS (2012) EUROGRAPHICS award for Outstanding Technical Contributions (2011) Irène Joliot Curie national award, mentorship category (2007) Junior member of the Institut Universitaire de France (1999) Professor Cani has supervised numerous students throughout her career and has led multiple significant research projects funded by prestigious organizations. Her ERC Advanced Grant EXPRESSIVE (2012-2017) focused on EXPloring RESponsive Shapes for the creation of Interactive Virtual Environnements. She created and led the STREAM Team at LIX from 2016-2019. More recently, she has been Principal Investigator in the chair between Google and Ecole Polytechnique on Artificial Intelligence & Visual Computing (2018-2021), and in the International Training Network CLIPE (2020-2024), funded by the European Research Council. She currently leads the interdisciplinary project Paleomob-3D (2023-2026) between LIX and HNHP, funded by CNRS 80-Prime. Professor Cani has led several research teams throughout her career, including the Imagine joint team (Inria/LJK lab, 2011-2016) and the Evasion joint team (Inria/GRAVIR lab, 2003-2010). She currently leads research in the LIX laboratory at Ecole Polytechnique, where she was the leader of the "Modeling Simulation and Learning" pole from 2019 to 2023.
Hyun Soo Park is an Associate Professor at the University of Minnesota, Twin Cities in the Department of Computer Science & Engineering . As a McKnight Presidential Fellow , his research focuses on computational social intelligence and egocentric perception , developing algorithms to model human interaction through gaze, facial expressions, and body gestures. He leads the Gemini-Huntley Robotics Research Lab and has secured major grants including NSF CAREER , Toyota Research Institute , and multiple NSF awards. Education : Ph.D. in Computer Science Teaching : Courses on 3D Computer Vision, Computer Vision, and Computational Linear Algebra (2017-2021) Research : Pioneering egocentric video analysis , 3D social signal modeling , and behavioral imaging with applications to robotics and human-computer interaction Scientific Awards include: NSF CAREER Award McKnight Presidential Fellow Guillermo E. Borja Award CVPR Best Paper Honorable Mention Grants secured: TRI (2021-2024) NSF NRI (2020-2023) NSF NCS (2020-2023) NIH R34 (2020-2022) NSF CRII (2018-2021) Minnesota Futures (2018-2021) Team includes: Meng-Yu Jennifer Kuo (Postdoc) 5 Ph.D. students (Yasamin Jafarian, Zhixuan Yu, etc.) Co-advised students with Prof. Roumeliotis and Prof. Guy Past members now at 3M and Adobe Research
Rémi Synave is an Associate Professor in the Department of Computer Science at the University of Strasbourg's Faculty of Science. His academic career spans over 15 years with continuous research output from 2006 to present, demonstrating sustained scholarly activity in computer graphics, 3D modeling, and interdisciplinary applications. Dr. Synave's research spans multiple domains with a strong focus on geometric algorithms, 3D reconstruction, and imaging applications. His work bridges computer science with anthropology, medicine, and cultural heritage preservation. Key research themes include geodesic path computation on triangular meshes, 3D surface reconstruction algorithms, medical imaging applications, and digital anthropology. His publications demonstrate consistent contributions to both theoretical computer graphics and practical applications across diverse fields. Analysis of his publication history reveals a strong trajectory from foundational geometric algorithms toward increasingly interdisciplinary applications. Early work focused on computational geometry and 3D reconstruction algorithms, while more recent publications demonstrate expansion into educational technology, image composition analysis, and digital humanities applications. His research consistently applies computer graphics techniques to solve domain-specific problems in anthropology, medicine, and cultural heritage. Rémi Synave maintains active collaborations with researchers across multiple institutions, particularly with Stefka Gueorguieva, Pascal Desbarats, and colleagues in anthropology and medical fields. His work on the Strasbourg Juvenile Collection represents a significant interdisciplinary contribution to digital anthropology. While specific teaching details aren't provided in the available materials, his publication on interdisciplinary arcade cabinet projects indicates innovative educational approaches. His laboratory work appears centered on 3D scanning, reconstruction, and visualization, with applications spanning from medical diagnostics to cultural heritage preservation. The consistent focus on algorithm development for geometric problems demonstrates a strong technical foundation applied across diverse practical contexts.
Jesus Alonso Alonso is a Researcher at the Department of Computer Science within the Faculty of Informatics of Barcelona (FIB) at the Technical University of Catalonia . His work bridges computational methods with geotechnical engineering challenges. Research Interests: Digital terrain modeling, bioengineering, computer-aided design, virtual reality, simulation, and video game development. His publications also reflect expertise in soil mechanics, landslide analysis, and mineral precipitation impacts on infrastructure. Key Projects: Development of novel data structures like the grounded heightmap tree for terrain representation, real-time rendering of dynamic terrains, and geotechnical studies on expansive claystones and liquefaction-induced landslides. Collaborations: Active with research groups such as ViRVIG (Visualization, Virtual Reality, and Graphic Interaction) and GIE (Informatics in Engineering).
