Chao Liu is a Research Scientist at CNRS (French National Center for Scientific Research) since 2008, affiliated with the DEXTER team and the Department of Robotics, LIRMM at University of Montpellier, France. He earned his Ph.D. in Electrical & Electronic Engineering from Nanyang Technological University, Singapore (2006). Current research focuses on surgical robotics , haptics , teleoperation , and nonlinear control theory with applications in computer vision. His work addresses challenges in robotic-assisted telesurgery, including: Stable and transparent human-robot interaction through wave variable compensators and passivity filters Physiological motion compensation using spatio-temporal LSTM and dual Kalman filters EMG-based motion recognition for surgical skill assessment 3D soft-tissue reconstruction with stereo-endoscopes and deep learning Dr. Liu leads European and French projects like: TS2RT (CNRS-funded): Safer teleoperation with motion compensation ROBACUS (ANR-funded): Needle positioning with MPC control HaTUMoCo (CNRS-funded): Haptic teleoperation with uncertainty handling ARAKNES (EU-funded): Microrobotic systems for endoluminal surgery Scientific honors include Senior Member of IEEE and Member of Sigma Xi . He supervises Ph.D. and Master's students working on topics such as concentric tube robot optimization, haptic teleoperation, and EMG-based force estimation. Dr. Liu serves on IEEE Technical Committees for Telerobotics and Haptics , and as Technical Editor of IEEE/ASME Transactions on Mechatronics.
Diogo Carbonera Luvizon is a Researcher at the Max-Planck-Institut für Informatik (MPI-INF) in Saarbrücken, Germany, and a member of the Visual Computing and Artificial Intelligence (VIA) Research Center. He holds a PhD in Computer Vision and Machine Learning from CY Cergy Paris University (2019), and Bachelor's and Master's degrees in Engineering and Applied Computing from UTFPR, Brazil. His research focuses on solving complex problems in Computer Vision, Computer Graphics, and Deep Learning, particularly in human modeling and real-time systems. Education: PhD (2019) - CY Cergy Paris University; M.Sc. (2015) - UTFPR; B.Sc. (2011) - UTFPR. Research interests include 3D human pose estimation, action recognition, multitask learning, and novel view synthesis. He has contributed to patents on multiplane image generation (Samsung) and vehicle speed measurement systems. His work has been recognized with awards like the Best Paper Honorable Mention at GCPR-VMV 2022 and Best Presentation Award at ETIS Lab (2018). He has developed open-source tools, including the deephar repository for human action recognition and pose estimation. His current affiliations include MPI-INF and the VIA Research Center, a partnership between MPI-INF and Google.
Richard Szeliski is a Distinguished Scientist at Google DeepMind and Affiliate Professor at the University of Washington's Department of Computer Science & Engineering. He previously led the Interactive Visual Media Group at Microsoft Research and founded the Computational Photography group at Facebook. His research focuses on computer vision, computer graphics, and numerical methods, with specialties in 3D modeling from imagery, computational photography, and neural rendering. Education details are not explicitly listed, but his career trajectory indicates advanced academic training in computer science. Research interests include algorithms for 3D reconstruction, image stitching, and optimization techniques. His recent work emphasizes neural rendering, volumetric representations, and large-scale scene modeling. Key contributions include the widely cited textbook Computer Vision: Algorithms and Applications and foundational papers on multi-view stereo, panorama stitching, and energy minimization in MRFs. Publications span 40+ years, with recent focus on radiance fields (NeRF), 3D scene understanding, and real-time rendering systems. Though no explicit awards are listed, his textbook adoption and industry roles reflect significant academic and industrial impact. He advises through his academic role and has contributed to open-source projects like the Bundle Adjustment Library (BAL). Labs/teams include collaborations with Google DeepMind, prior work at Microsoft Research's Interactive Visual Media Group, and academic partnerships at UW's Graphics & Imaging Lab. His work bridges theory and application, addressing challenges in both academic research and industrial-scale systems.
Professor David Taubman is a distinguished academic serving as Professor and Deputy Head of School (Research) at the School of Electrical Engineering and Telecommunications (EE&T) at the University of New South Wales (UNSW) in Sydney, Australia. He is also co-director of Kakadu Software Pty. Ltd. and its affiliates Kakadu R&D and Kakadu GPU. With a career spanning over three decades, Professor Taubman has made significant contributions to the field of image and video compression, most notably as the author of the EBCOT coding algorithm adopted in the JPEG2000 international standard. Professor Taubman earned his B.Sc. in Mathematics and Computer Science (1986) and B.E. (Medal) in Electrical Engineering (1988) from the University of Sydney, followed by an M.Sc. (1992) and Ph.D. (1994) in Electrical Engineering from the University of California at Berkeley. His professional journey includes engineering work at the Electricity Commission of N.S.W. (1988-1990), research positions at Hewlett-Packard Laboratories in Palo Alto (1994-1998), and an academic career at UNSW where he progressed from Senior Lecturer (1998-2003) to Associate Professor (2004-2009) and finally to Professor (2009-present). He has held various leadership roles including Head of the EE&T Telecommunications Research Group (2003-2014), Head of the EE&T Signal Processing Research Group (2014-present), Director of Research for the School of EE&T (2011-2016), and Deputy Head of School (Research) since 2017. Professor Taubman's research interests center on image and video compression, with particular expertise in JPEG2000 standards and implementations. His work spans signal processing, wavelet transforms, scalable video coding, motion modeling, and multimedia systems. He has pioneered numerous compression algorithms and frameworks, including the EBCOT coding algorithm that became central to the JPEG2000 standard. His recent research focuses on efficient motion modeling with cuboidal partitioning, learned lifting-based transform structures, and high-throughput implementations of JPEG2000 for video applications. His work bridges theoretical foundations with practical implementations, as evidenced by the commercially successful Kakadu Software tools that have garnered around 500 commercial licensees. Analysis of Professor Taubman's recent publications reveals a consistent focus on advancing compression technologies with particular emphasis on scalability, efficiency, and adaptability. His work spans traditional image compression (JPEG2000 extensions), video coding (cuboid-based partitioning for UHD/360-degree video), and emerging applications (nanopore sequencing data compression). A notable trend is the integration of machine learning techniques with traditional compression frameworks, as seen in his work on learned lifting-based transform structures. His research maintains strong connections to real-world applications across diverse domains including medical imaging, astronomical data processing, and genomic sequencing. IEEE Fellow Engineers Australia Fellow (by invitation) Professor Taubman has served as Associate Editor for the IEEE Transactions on Image Processing for two four-year appointments (2003-2005 and 2010-2013). He has been actively involved in numerous research grants focused on image and video compression technologies, particularly those related to the JPEG2000 standard and its extensions. His work has received significant industry support, reflected in his consultancy with various U.S., Japanese, and Australian corporations. He has also contributed to international standards development as a member of Standards Australia Technical Committee MS-065 (mirroring ISO TC42 on Digital Photography) and as a constitutional member of Standards Australia Technical Committee IT-029 (Coded Representation of Picture, Audio and Multimedia/Hypermedia Information). Professor Taubman co-directs Kakadu Software Pty. Ltd. and its research affiliates Kakadu R&D and Kakadu GPU, which have developed the commercially successful Kakadu Software tools for JPEG2000. His research group at UNSW focuses on advanced image and video compression techniques, with particular expertise in wavelet-based methods, scalable coding, and motion modeling. The group maintains strong industry connections and has contributed significantly to the development and standardization of image compression technologies worldwide.
Huaizu Jiang is an Assistant Professor at Khoury College of Computer Sciences, Northeastern University. His research bridges computer vision, graphics, and natural language processing to develop AI systems that understand and reconstruct 3D visual environments. Prior to joining Northeastern, he was a Postdoc Researcher at Caltech and Visiting Researcher at NVIDIA. He holds a Ph.D. from UMass Amherst (advised by Prof. Erik Learned-Miller), and M.E./B.E. degrees from Xi'an Jiaotong University. His research focuses on fundamental challenges in 3D scene understanding, including geometry reconstruction, semantic interpretation, novel view synthesis, motion generation, and optical flow estimation. Core interests span video processing, human-object interactions, multimodal reasoning, and efficient edge-device implementations. Recent publications emphasize diffusion models for motion/scene generation, transformer-based 3D perception, and video interpolation. Key trends include multi-view consistency techniques, text-to-3D synthesis, and efficient real-time algorithms for robotics applications. Awards & Honors: Winner of the VQA Challenge 2020 He advises 15+ graduate students on projects spanning 3D reconstruction, motion synthesis, and vision-language models. His group collaborates with institutions like NVIDIA and Caltech, focusing on generative AI for dynamic scene understanding.
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.
Vincent Sitzmann is an Assistant Professor at the Massachusetts Institute of Technology (MIT), affiliated with the Computer Science and Artificial Intelligence Laboratory (CSAIL). He leads the Scene Representation Group and is part of the Visual Computing research community at CSAIL. His work focuses on advancing artificial intelligence's ability to perceive and interact with the physical world, particularly through neural fields, 3D scene representations, and robotics. His research bridges computer vision, machine learning, and robotics, aiming to create systems that emulate human perception and decision-making. He holds a dual role in the PI Core/Dual program at MIT and contributes to interdisciplinary efforts in AI & ML, Graphics & Vision, and Robotics. His recent projects include developing generative models for 3D avatars, robust camera pose estimation, and learning-based control for soft robots. He collaborates widely within MIT’s engineering ecosystem and has led initiatives such as the Collaborative Research grant on compositional implicit representations for 3D scene understanding (2022). His lab, the Scene Representation Group, emphasizes scalable 3D reconstruction, material estimation, and embodied AI. Notable technologies include Flowmap for camera calibration and Dittogym for soft robotics control. While no awards are explicitly listed, his work has been featured in top conferences like SIGGRAPH and IEEE Robotics.
Dr. Wan Renjie is an Assistant Professor in the Department of Computer Science at the Faculty of Science, Hong Kong Baptist University (HKBU). He holds a BEng in Network Engineering from the University of Electronic Science and Technology of China and a PhD from Nanyang Technological University (NTU), Singapore. Prior to joining HKBU, he was a Wallenberg-NTU Presidential Postdoctoral Fellow (2020–2022) and a guest researcher at Peking University (2019–2020). His research focuses on computational photography, 3D vision, AI security, digital watermarking, and neural representations . He explores robustness and security in vision models, especially concerning NeRFs and 3D Gaussian Splatting, and develops methods for low-light enhancement, reflection removal, and domain adaptation. Dr. Wan has published in top-tier venues including TPAMI, IJCV, CVPR, ICCV, NeurIPS, AAAI, and ECCV . His recent work emphasizes copyright protection for neural 3D models , adversarial attacks in multimodal and event-based systems, and medical image reconstruction. He is actively mentoring PhD students and research assistants. VCIP 2020 Best Paper Award Outstanding Reviewer, ICCV 2019 He teaches courses such as Introduction to AI and ML (COMP3057) , AI Application Development (COMP3065) , and Python for Data Analysis and Machine Intelligence (COMP7035) . Dr. Wan leads a dynamic research group with ongoing projects on watermarking, 3D reconstruction, and AI security, and he is currently recruiting new PhD students and research assistants.
Professor Adrian Hilton is a distinguished faculty member at the University of Surrey, serving as Director of the Centre for Vision, Speech and Signal Processing (CVSSP) and Director of the Surrey Institute for People-Centred AI. He is affiliated with the School of Computer Science and Electronic Engineering and leads the Visual Media Research Lab (V-Lab). His research focuses on pioneering next-generation 4D computer vision technologies that enable machines to understand and model dynamic real-world scenes. Key areas include 3D/4D shape capture, computer vision, machine learning, graphics, and animation for applications in sports analysis, film/TV production, virtual reality, and medical imaging. His work bridges the gap between real and computer-generated imagery, with notable contributions in volumetric capture, motion capture, and free-viewpoint video. Hilton's recent publications demonstrate a strong trend toward multimodal integration, particularly combining audio and visual processing for spatial audio applications, while advancing 4D reconstruction techniques for human performance capture. His work increasingly incorporates transformer architectures and neural rendering techniques for improved illumination estimation, shadow modeling, and multi-view consistency. Scientific Awards and Recognition Two EU IST Innovation Prizes Manufacturing Industry Achievement Award Royal Society Industry Fellowship (2008-2011) Royal Society Wolfson Research Merit Award in 4D Vision (2013-2018) Fellow of the Royal Academy of Engineering (FREng) Fellow of the International Association for Pattern Recognition (FIAPR) Fellow of the Institution of Engineering and Technology (FIET) Hilton actively mentors PhD and post-doctoral researchers through his leadership of CVSSP, which has a grant portfolio exceeding £31M and comprises 170 researchers. He has successfully commercialized several technologies, including systems used by the BBC for sports commentary visualization. His research collaborations span major industry partners including BBC, BT, Sony, Framestore, and The Foundry. He co-founded the G3 Games forum and the CVMP Conference on Visual Media Production, demonstrating strong engagement with the creative industries. Current research projects include the S3A Programme Grant in Future Spatial Audio and InnovateUK's ALIVE project for 360 video reconstruction.
Laurent Caraffa is a Researcher at Université Gustave Eiffel, working at the LaSTIG laboratory of IGN (National Institute of Geographic and Forest Information). His research focuses on large-scale 3D data processing, including surface reconstruction from point clouds and images, leveraging triangulated structures and implicit methods. His work also covers indexing and searching within point clouds for large-scale place recognition, with applications in urban environments and navigation systems. Caraffa's research interests span 3D Data Processing, Surface Reconstruction, Point Cloud Processing, Large-scale Place Recognition, Indexing and Retrieval, Big Data, Cloud Computing, Mathematical Optimization, 3D Mapping, and Photogrammetry in degraded conditions. His work bridges theoretical computational geometry with practical applications in geographic information systems and autonomous navigation. His publication record demonstrates significant contributions to distributed 3D processing, particularly through advancements in Delaunay triangulation, watertight surface reconstruction, and neural radiance fields. Recent work shows a clear trajectory toward more efficient and scalable methods for processing massive 3D datasets, with growing emphasis on implicit representations and learning-based approaches for 3D reconstruction. Caraffa actively participates in the scientific community through organizing events like the Big Data Day 2023 at IGN and contributing to major research projects. His work has resulted in publications in top-tier conferences including ICLR, CVPR, ISPRS, and IEEE Big Data, establishing him as a significant contributor to the field of large-scale 3D data processing. As a research supervisor, Caraffa currently co-supervises four PhD students working on projects funded by AID, Criteo, and Huawei, focusing on large-scale place recognition, implicit representations for 3D reconstruction, and 3D reconstruction in degraded conditions. He is also the co-founder of ExtraLabs, a company developing distributed computing solutions for cooperative digital twins, demonstrating the practical impact of his research.
Dr. Minglun Gong is a Professor and Director of the School of Computer Science at the University of Guelph (since 2019). Previously, he served as Professor and Head of the Department of Computer Science at Memorial University of Newfoundland. He holds a Ph.D. from the University of Alberta (2003), M.Sc. from Tsinghua University (1997), and B.Engr. from Harbin Engineering University (1994). His research focuses on visual computing, including computer graphics, computer vision, visualization, image processing, and pattern recognition. He has authored over 150 referred papers and holds patents in the field. He is an Associate Editor for Pattern Recognition and IEEE Signal Processing Letters , and has received awards such as the Izaak Walton Killam Memorial Award and multiple best paper awards. Dr. Gong has advised numerous students, including Ph.D./M.Sc. candidates and visiting scholars. His lab's recent work includes UAV path planning for urban reconstruction, image stylization techniques, and 3D human pose estimation. He actively participates in academic service, including editorial roles, conference program committees, and administrative roles at multiple institutions. His teaching spans courses in image processing, computational photography, and technical communication. He is also involved in administrative committees, such as Graduate Studies and Promotion at Memorial University. Key research contributions include advancements in transparent object modeling, underwater 3D reconstruction, and image-to-image translation. His work emphasizes practical applications in fields like medical imaging, autonomous systems, and environmental modeling.
Dr. Yun Zhang is a Professor and Canada Research Chair in the Department of Geodesy and Geomatics Engineering at the University of New Brunswick. He holds a PhD from the Free University of Berlin and has pioneered research in remote sensing, image processing, and computer vision since 2000. His patented technologies are licensed to global companies including PCI Geomatics and DigitalGlobe. Research Focus: Optical/radar image processing, digital photogrammetry, AI applications in geomatics, and sensor fusion for UAV systems. His work enables advanced geospatial analysis across environmental, urban, and defense sectors. Distinctions: First Giuseppe Inghilleri Award (ISPRS 2012) NSERC Synergy Innovation Award from Governor General of Canada (2011) ASPRS Talbert Abrams Grand Award (2005) Featured in CFI 20th Anniversary Book for breakthrough innovations Technology Impact: Solutions deployed by NASA, USGS, Google Earth, and DND Canada across five continents. Recognized among top 9 Canadian research achievements in AUTM's global case studies alongside MIT and Stanford innovations.
Oscar Mendez Maldonado is a Lecturer in Robotics and Artificial Intelligence at the University of Surrey's School of Computer Science and Electronic Engineering, affiliated with the Robotics Department and CVSSP Centre. He holds a PhD (2018) and BEng (2013) from the University of Surrey. His research focuses on Machine Learning, Computer Vision, and Robotics, with emphasis on autonomous systems, localisation, and SLAM applications. Key projects include the Autonomous Valet Parking (AVP) system for indoor navigation and the SMILE project for sign language assessment using AI. He has supervised students like James Ross (Autonomous Vehicles), Xihan Bian (Reinforcement Learning), and Nimet Kaygusuz (Visual Odometry). Notable achievements include the Sullivan Thesis Prize (2018) and impactful publications in IEEE conferences (e.g., ICRA, CVPR, IROS). Research spans topics like 3D hand pose estimation via diffusion models, graph-based visual odometry fusion, and Raman spectroscopy for localisation. He contributes to open-source tools (e.g., RaSpectLoc GitHub) and collaborates with industry partners like Parkopedia. His work bridges theoretical advances with real-world applications in autonomous systems and healthcare.
Ioannis Stamos is a Professor of Computer Science at Hunter College, City University of New York (CUNY), within the School of Arts and Sciences. His research focuses on Computer Vision, Robotics, Computer Graphics, and 3D Visualization, with emphasis on 3D modeling using range and image data. He earned his Ph.D. in Computer Science from Columbia University (2001), followed by an M.S. and M.Phil. from Columbia's Computer Science Department, and a Diploma of Engineering from the University of Patras, Greece. Dr. Stamos has received prestigious awards including the NSF CAREER Award (2003) and Google Research Awards (2014, 2017). His work integrates 2D images and 3D range data for urban scene modeling, sensor fusion, and real-time object detection. Notable contributions include advancements in 6DoF pose estimation, LiDAR-based curb detection, and Kronecker product models for repeated patterns in urban imagery. He leads the Computer Vision & Robotics Lab and teaches graduate courses in 3D Computer Vision and Photorealistic Modeling. His research is supported by NSF grants, including MRI awards for mobile robotics and large-scale 3D modeling. He serves as Area Editor for the Journal of Computer Vision and Image Understanding and has co-chaired conferences like 3DV 2013. His lab collaborates on projects involving procedural modeling of urban environments and online classification of 3D point clouds.
Professor Pascal Fua is a distinguished faculty member at EPFL (Swiss Federal Institute of Technology) in the School of Computer and Communication Science. He joined EPFL in 1996 and currently serves as Head of the Computer Vision Laboratory (CVLAB). His extensive research spans multiple cutting-edge areas in computer vision and geometric deep learning, with applications ranging from 3D reconstruction to medical imaging and aerodynamic optimization. Dr. Fua's research interests encompass Computer Vision, 3D Reconstruction, Shape Modeling, Geometric Deep Learning, Medical Image Analysis, Augmented Reality, Motion Recovery, Surface Mesh Processing, and Aerodynamic Shape Optimization. His work demonstrates a remarkable ability to bridge theoretical computer vision with practical applications across diverse domains. His research has evolved from traditional geometric computer vision techniques to incorporating deep learning approaches for 3D modeling, with recent focus on differentiable rendering, implicit surface representations, and applications in medical imaging and engineering design. His publication record shows a consistent trajectory of high-impact research, with recent work focusing on differentiable iso-surface extraction, geometric deep learning for aerodynamic shape optimization, and novel approaches to 3D reconstruction. His work spans both theoretical advances in computer vision algorithms and practical applications in medical imaging, autonomous driving, and computational fluid dynamics. IEEE Fellow Multiple ERC Grants recipient Associate Editor of IEEE Transactions for Pattern Analysis and Machine Intelligence Throughout his career, Professor Fua has mentored numerous PhD students who have gone on to make significant contributions in computer vision and related fields. His laboratory has established collaborations across multiple disciplines, including medical imaging, aerospace engineering, and neuroscience, demonstrating the broad applicability of his research. His current work continues to push the boundaries of geometric deep learning and 3D vision, with particular emphasis on making these techniques more practical and applicable to real-world engineering and medical problems.
