Franziska Mueller is a Research Scientist at Google Zurich , specializing in Augmented Perception . Prior to joining Google, she earned her Ph.D. in Computer Science at Saarland University under the supervision of Prof. Dr. Christian Theobalt, focusing on real-time hand reconstruction from RGB and depth images. Ph.D. in Computer Science (2016-2020) at Saarland University Master’s and Bachelor’s in Computer Science at Saarland University Research visits at Stanford University (2018) and Reality Labs Research (2019) Her research emphasizes the integration of model-based techniques and machine learning components for real-time 3D hand pose estimation, occlusion handling, and hand-object interaction tracking. Key contributions include methods for single-camera reconstruction and datasets like HandSeg. Scientific Awards : Dr. Eduard Martin Award (2021) Google PhD Fellowship (2017) Günter-Hotz-Medal (2016) Bachelor Award (2015) Völklinger Abiturpreis (2012)
Siyu Tang is an Assistant Professor in the Department of Computer Science at ETH Zürich, where she leads the Computer Vision and Learning Group (VLG) at the Institute of Visual Computing. Her research focuses on computational models for human perception and digitalization through computer vision and machine learning. Her educational background includes: PhD in Computer Science, Max Planck Institute for Informatics (2017), supervised by Prof. Bernt Schiele Master of Science in Media Informatics, RWTH Aachen University Bachelor of Science in Computer Science, Zhejiang University, China Dr. Tang specializes in human-centric computer vision, developing statistical models for motion analysis, pose estimation, and digital human creation. Her work integrates machine learning with optimization techniques to enable machines to interpret human activities from visual data, with applications spanning virtual reality, healthcare, and human-computer interaction. Key research thrusts include generative models for content creation, egocentric vision, and human motion synthesis. Her recent publications (2024-2025) demonstrate intense focus on 3D human modeling and neural rendering, with Gaussian splatting emerging as a dominant technique for efficient avatar creation and scene reconstruction. Significant themes include text-driven motion synthesis using diffusion models, relightable avatars, surgical training applications, and egocentric multimodal pretraining. This work bridges computer vision, graphics, and machine learning to advance human digitalization. No scientific awards were mentioned in the provided text. Dr. Tang leads the VLG research group at ETH Zürich, mentoring PhD and Master's students in human-centric AI. She previously secured an early career research grant from the Max Planck Institute for Intelligent Systems to establish her independent research program. Her group actively pursues funding for projects in human motion analysis, 3D reconstruction, and generative modeling, with strong industry and clinical collaborations. The Computer Vision and Learning Group (VLG) operates within ETH's Institute of Visual Computing, maintaining dedicated facilities for motion capture, 3D scanning, and high-performance computing. The team collaborates internationally with institutions like the Max Planck Society and focuses on scalable solutions for real-world human digitalization challenges, including surgical training systems and immersive virtual environments.
Dr. Frederick Li is an Associate Professor in the Department of Computer Science at Durham University, UK. He holds editorial roles as Associate Editor of Frontiers in Education (Digital Education) and Editorial Board Member of Virtual Reality & Intelligent Hardware. His research focuses on Computer Graphics, Machine Learning, Geometric Modelling, Collaborative Virtual Environments, Visual Aesthetics, and Educational Technologies. He earned his B.A. (Hons) and M.Phil. from The Hong Kong Polytechnic University and his Ph.D. in Computer Graphics from City University of Hong Kong. Prior roles include Assistant Professor at HK PolyU and project manager of a Hong Kong Government ITF-funded project. **Education**: B.A. (Computing Studies) and M.Phil. from HK PolyU; Ph.D. in Computer Graphics (CityU Hong Kong). **Research Interests**: His work spans mesh saliency detection, human-object interaction recognition, cloud modeling, face beautification, and educational technology. Recent achievements include awards for papers (e.g., Best Paper at ITiCSE 2014) and recognition such as EPSRC Peer Review College membership. He leads Durham's Undergraduate Board of Examiners and has been an external examiner at Northumbria University. **Awards**: Best Paper (ACM ITiCSE 2014), Outstanding Paper (ICALT 2013), EPSRC Peer Review College (2024), Outstanding BMVC 2024 Reviewer. **Grants & Labs**: His research is supported by grants from EPSRC and others. He collaborates with the Centre for Vision and Visual Cognition, VIViD, and AIHS group at Durham.
Maks Ovsjanikov is a Professor in the Computer Science Department at École Polytechnique, France , and a Visiting Research Scientist at Google DeepMind. His research focuses on mathematically principled approaches for geometric data analysis and synthesis, including learning on surface meshes, 3D point clouds, and graphs. Key Collaborations: Google DeepMind, Sanofi, Dassault Systèmes Research Themes: Non-rigid shape matching, 3D reconstruction, transfer learning, learning on geometric data, functional maps, deep learning for scientific discovery Recent Article Trends emphasize geometric deep learning, with publications at top venues like SIGGRAPH Asia, ICCV, and CVPR. Topics include surface reconstruction, functional maps, 3D keypoint detection, and diffusion models for shape matching. Scientific Honors include: ERC Consolidator Grant (VEGA Project, 2023) ERC Starting Grant (2017) ACM SIGGRAPH 2023 Test-of-Time Award Best Paper Awards at 3DV 2021 and 3DV 2022 Student Advisees have received prestigious awards, such as the IP Paris Best PhD Thesis Award (Souhaib Attaiki, 2023) and GdR IG-RV Runner-Up (Nicolas Donati, 2024). The GeomeriX Team at École Polytechnique drives his group's research, supported by the VEGA and AIGRETTE projects.
Lawrence H. Staib is a Professor of Biomedical Engineering at Yale University, with additional academic appointments in Electrical & Computer Engineering and Radiology & Biomedical Imaging. He holds a Ph.D. from Yale University and specializes in automated medical image analysis, including techniques like model-based segmentation, nonrigid registration, and diffusion tensor imaging (DTI). His research focuses on applications in neuroscience, cardiology, and cancer imaging, emphasizing machine learning and functional MRI analysis. His key contributions include advancements in white matter tractography via anisotropic wavefront evolution, real-time neural tract parcellation (Fasciculography), and noise reduction in diffusion tensor fields. Staib is a Fellow of the American Institute for Medical and Biological Engineering (2015), recognizing his impactful work in medical imaging technologies. Staib's research also encompasses statistical deformation models, perturbation-based shape analysis, and 3D deformable models for volumetric segmentation. He has developed patented 3D ultrasound computed tomography systems (USPTO #6878115, 7025725). His work bridges clinical needs with computational methods, addressing challenges in image registration, structural connectivity analysis, and medical robotics.
Changjian Li is an Assistant Professor in the School of Informatics at the University of Edinburgh. He leads the GraphViX Group (Graphics, Vision and X) and is a member of the Institute of Perception, Action and Behaviour (IPAB). His research spans computer graphics, computer vision, and human-computer interaction with a focus on 3D generation and analysis. Education: Bachelor's Degree from Shandong University (2014) Ph.D. from the University of Hong Kong (2019) under Prof. Wenping Wang Postdoc at University College London (UCL) with Prof. Niloy Mitra Starting Researcher position at Inria with Dr. Adrien Bousseau Research Interests: Changjian's research focuses on sketch-based 3D modeling, CAD modeling, point cloud processing, and medical imaging applications. He develops systems that bridge intuitive sketching with precise CAD workflows, enhances 3D animation pipelines, and applies neural methods to sparse medical data reconstruction. Scientific Recognition: Best Paper Honorable Mention Award (MICCAI 2021) CADTalk selected as Highlight (CVPR 2024 top 10%) ACM SIGGRAPH Asia 2018 cover image selection ACM SIGGRAPH Asia 2015 technical paper highlight CVPR 2019 poster highlighted in 'Computer Vision News' Advising & Collaborations: He mentors postdocs and PhD students including Duolikun Danier, Haocheng Yuan, Ankan Bhunia, and Lei Zhong. Former advisees include Salvatore Esposito (now at Edinburgh), Guangshun Wei (Shandong University), and Mingjun Yang (University of Melbourne). Collaborates with Oisin Mac Aodha, Hakan Bilen, and Niloy Mitra. Professional Service: Currently serves as Associate Editor for IEEE TVCG and participates in program committees for SIGGRAPH Asia, SIGGRAPH, EuroGraphics, and Geometry Design and Computing (GDC) conferences.
João Paulo Costeira is an Associate Professor at the Department of Electrical and Computer Engineering, Instituto Superior Técnico (IST), Lisbon. He holds a PhD in Electrical and Computer Engineering from IST (1995) and was a Visiting Scientist at Carnegie Mellon University's Robotics Institute (1991–1995). His research focuses on Computer Vision, 3D Reconstruction, and Structure from Motion, with contributions to object recognition, robotics, and multimedia analysis. Education: PhD in Electrical and Computer Engineering, IST (1995); Visiting Scientist, CMU Robotics Institute (1991–1995). Roles: Coordinator of the Signal and Image Processing Group (SIPg), Co-director of the Carnegie Mellon|Portugal Dual PhD Program in ECE and Robotics (2007–2018), and Scientific Director of Carnegie Mellon|Portugal (2014–2018). Research Interests: João's work emphasizes 3D reconstruction from video, rigid and non-rigid motion analysis, and applications in robotics and urban surveillance. He has pioneered methods for motion segmentation and robust correspondence problems in computer vision. Publications: His recent work includes advancements in apple counting systems, rotation averaging for robotics, and domain adaptation for traffic density estimation. These contributions highlight his expertise in real-world computer vision challenges. Awards: None explicitly listed. However, his extensive publication record and academic leadership reflect significant scholarly impact. Advising & Grants: Supervised 13 PhD students, many co-advised with CMU faculty. Active in projects like CityCam (vehicle counting) and MultiDrone (robotics collaboration). Funded by FCT, EU, and industry partnerships. Labs/Teams: Leader of the Signal and Image Processing Group (SIPg) at ISR. Involved in NETSyS program for networked systems and robotics.
Steven Ceron is an Assistant Professor in Robotics at the University of Michigan's College of Engineering. His research focuses on swarm robotics, multi-agent systems, and programmable self-organization of micro- and macro-scale robot swarms. He leads the Synergetic Adaptive Machinas (SAM) Lab, which develops reconfigurable robot swarms for biomedical applications and smart materials integration. Key research areas include microrobot fabrication, heterogeneous swarm coordination, and self-reconfigurable modular systems. His work envisions seamless integration of robot swarms into daily life through innovations in design, control, and scalability. Recent publications emphasize swarmalator dynamics, strain-based coordination in soft robots, and scalable fabrication methods. His lab explores both theoretical frameworks and practical implementations, bridging micro-scale and macro-scale robotics applications. Though no awards were explicitly listed, his contributions to novel fabrication techniques and modular robotics suggest ongoing recognition in the field. Advising and grant details are not provided here, but his lab's focus on biomedical and aerospace applications indicates active collaborative projects.
Gerard Pons-Moll is a Professor at the University of Tübingen, endowed by the Carl Zeiss Foundation, and heads the Emmy Noether independent research group 'Real Virtual Humans'. He is a core faculty member at the Tübingen AI Center, a senior researcher at the Max Planck Institute for Informatics (MPII), and faculty at the International Max Planck Research School for Intelligent Systems (IMPRS-IS) and the Saarland Informatics Campus. His research focuses on computer vision, graphics, and machine learning, particularly in creating virtual human models and analyzing human motion from video and sensor data. Education: PhD (with distinction) in 2014 from Leibniz University of Hannover, Master's in Telecommunications Engineering (Northeastern University, 2008), and B.S./M.Sc. in Telecommunications Engineering from the Technical University of Catalonia (2002–2008). Research Interests: 3D human modeling, pose estimation, human-object interaction, and applications in industry and research. His work emphasizes real-world applications like virtual avatars and motion capture systems. Awards: Emmy Noether Grant (2018), German Pattern Recognition Award (2019), Google Faculty Research Award (2019), and multiple best paper awards at top conferences (BMVC’13, Eurographics’17, 3DV'18, CVPR'20). Advising & Grants: Served as program chair of 3DV 2021, area chair for ECCV, CVPR, and IJCAI. Active in reviewing for DFG, ANR, and ISF. Supervises research in areas like neural rendering frameworks (Blendify) and synthetic data generation (STAGE). Labs/Teams: Leads the Emmy Noether group and collaborates with MPII, Tübingen AI Center, and IMPRS-IS on projects like XNect (real-time 3D motion capture) and Human 3Diffusion (avatar creation).
Mohamed Hefeeda is a Professor in the School of Computing Science at Simon Fraser University (SFU), Canada. He leads the Network and Multimedia Systems Lab (NMSL) and previously served as Director of the School from 2018 to 2023. His research focuses on multimedia networking, mobile computing, cloud systems, and hyperspectral imaging. He holds an ACM Distinguished Member designation and has received prestigious awards including the NSERC Discovery Accelerator Supplements (2011) and multiple best paper awards at top conferences like ACM MM and IEEE Infocom. Education: Ph.D., Purdue University, 2004 M.Sc., University of Connecticut, 2001 B.Sc., Mansoura University, Egypt, 1994 Research Interests: Design of efficient multimedia systems and protocols for wired/wireless networks Cloud gaming optimization and video encoding techniques Hyperspectral imaging for healthcare and mobile applications AI-driven multimedia systems and mobile computing innovations Grants & Industry Collaborations: Funded by NSERC, CFI, and companies like AMD, Huawei, and CBC Co-founded Video Semantics (acquired by tech firm) Partnered with CBC on peer-assisted content distribution systems Awards Highlights: 2025: ACM Distinguished Member 2019: Best Student Paper Award at ACM MMSys 2015: NSERC Discovery Accelerator Supplements Labs & Leadership: Network and Multimedia Systems Lab (NMSL) at SFU Contributed to creation of Qatar Computing Research Institute (QCRI)
Rekha R. Thomas is a Professor of Mathematics and Undergraduate Program Director at the University of Washington. She holds a Ph.D. in Operations Research from Cornell University (1994), with postdoctoral experience at Yale University and the Konrad-Zuse-Zentrum in Berlin. Her research focuses on optimization, applied algebraic geometry, and computer vision, with contributions to semidefinite programming, graphical designs, and geometric algorithms. She has held distinguished positions such as the Robert R. and Elaine F. Phelps Professorship (2008–2012) and the Robert B. Warfield Jr. Faculty Fellowship (2017–2020). Her work bridges theory and application, addressing challenges in computer vision, combinatorial optimization, and algebraic geometry. Notable contributions include advancements in multiview geometry, kernel learning, and the geometric analysis of rank-deficient matrices. She actively collaborates across disciplines, publishing extensively and supervising numerous graduate students and postdocs. Rekha also engages in academic leadership, mentoring students, and participating in international conferences. Her research has been recognized through invited talks at major events like the International Congress of Mathematicians (2018) and SIAM Annual Meetings. She continues to explore the intersections of algebraic geometry, optimization, and computational methods.
Marc Pollefeys is a Full Professor of Computer Science at ETH Zurich and Director of the Microsoft Mixed Reality and AI Zurich Lab. He has held roles such as Visiting Professor at Stanford University (2007) and Assistant/Associate Professor at UNC-Chapel Hill (2002–2009). His research focuses on 3D computer vision, robotics, machine learning, and augmented reality. Education: PhD in Computer Science from KU Leuven (1999), followed by postdoctoral research there until 2002. He transitioned to academic roles at UNC-Chapel Hill before joining ETH Zurich in 2007. Research interests include 3D reconstruction, visual localization, SLAM, and applications in archaeology, urban modeling, and robotics. Notable projects include real-time 3D scanning, city-scale reconstruction, and autonomous vision-based drones. Key awards include ACM Fellow (2022), IEEE Fellow (2012), and ERC Starting Grant (2008). He advises numerous PhD students and collaborates with institutions like Google and Microsoft. Labs and teams: Leads the Computer Vision and Geometry (CVG) lab at ETH Zurich and directs the Microsoft Mixed Reality and AI Lab. His work bridges academia and industry, focusing on perception for mixed reality and autonomous systems.
Jia-Bin Huang is an Associate Professor in the Department of Computer Science at University of Maryland, College Park , with a secondary appointment at the University of Maryland Institute for Advanced Computer Studies . His work bridges computer vision , computer graphics , and machine learning . His research focuses on 3D scene reconstruction , neural radiance fields , generative models , and multimodal foundation models . He has made significant contributions to video super-resolution , text-driven 3D modeling , and inverse rendering techniques. 15 recent publications (2024-2025) at top venues: CVPR , NeurIPS , SIGGRAPH Asia , 3DV , and ECCV Pioneering work in Urban Scene Inverse Rendering , Generative Video Editing , and 3D Human Digitization He has received multiple awards including the 3M Non-Tenured Faculty Award , ETRA Best Paper , and NSF Grants . His lab trains 12 PhD students and has graduated 18 Masters/PhD students now at institutions like Stanford , Meta , and Google .
Prof Nikolaos Nikiforakis is a Professor at the University of Cambridge, leading the Laboratory for Scientific Computing at the Cavendish Laboratory. He holds roles including Director for Academic Programmes of the Centre for Scientific Computing, Course Director of the MPhil in Scientific Computing, and Deputy Director of the EPSRC Centre for Doctoral Training in Computational Methods for Materials Science. He is also a Fellow and Director of Studies in Mathematics at Selwyn College, Cambridge. He directs The Gianna Angelopoulos Programme for Science Technology and Innovation. He holds a BSc in Aeronautical Engineering from the University of Manchester, followed by an MSc in Aerospace Propulsion and a PhD in 'Evolution of Detonation Waves' from Cranfield Institute of Technology. His postdoctoral research at the University of Cambridge’s Department of Chemistry focused on computational models for stratospheric ozone depletion. He later founded the Laboratory of Computational Dynamics at the Department of Applied Mathematics and Theoretical Physics before joining the Cavendish Laboratory in 2008. His research focuses on numerical algorithms and High Performance Computing for multi-physics simulations involving complex systems of nonlinear PDEs. Applications span detonation dynamics, plasma physics, and materials science, with industry collaborations for software development. His work addresses multi-scale, multi-physics problems previously deemed intractable, with practical applications in aerospace, energy, and environmental fields. He leads academic programmes in scientific computing and supervises doctoral research through the EPSRC CDT. His contributions bridge fundamental science and industrial innovation, emphasizing computational methods for materials and fluid dynamics.
Nianyi Li is an Assistant Professor in the School of Computing at Clemson University. He holds a B.E. in Electronic and Information Engineering from Huazhong University of Science and Technology and a Ph.D. in Computer and Information Sciences from the University of Delaware. His research focuses on machine learning, computer vision, computational photography, and medical image processing. He has served as an Area Chair for NeurIPS 2024 and CVPR 2023/2024, demonstrating leadership in the academic community. Education: Ph.D., Computer and Information Sciences, University of Delaware (Advisor: Jingyi Yu) B.E., Electronic and Information Engineering, Huazhong University of Science and Technology Research Interests: Machine Learning Computer Vision Computational Photography Medical Image Processing His work includes contributions to atmospheric turbulence removal, microscopy video denoising, and deep learning applications in medical imaging. Key projects include the 'Turb-Seg-Res' pipeline for dynamic video restoration and the NimBLE non-rigid hand model. Recent articles focus on unsupervised methods for object segmentation, fluid surface reconstruction, and medical image analysis. Awards and grants are not explicitly listed but reflect his active research contributions.
