جستجوی استاد راهنمای دانشگاهی

Lan Xuمشاهده پروفایل

استادیار

• Computer Vision
• Computer Graphics
• Performance Capture
• +۵ مورد دیگر

Lan Xu is a Tenure-track Assistant Professor at the School of Information Science and Technology (SIST) in ShanghaiTech University. His research focuses on computer vision and computer graphics, specifically on capturing, perceiving, and understanding human-centric dynamic and static scenes in complex real-world environments. Dr. Xu received his Ph.D. from the Hong Kong University of Science and Technology (HKUST) in 2020 under Prof. Lu Fang, and his B.E. from Zhejiang University (ZJU) in 2015. Prior to ShanghaiTech, he worked with Prof. Yebin Liu at Tsinghua University (2016) and visited the GVV group at MPI hosted by Prof. Christian Theobalt (2018). His research spans performance capture, 3D/4D reconstruction, scene understanding, and artificial reality , aiming to digitalize humans, objects, and events for realistic tele-presence in VR/AR. His work targets the intersection of computer vision, computer graphics, and machine learning with significant practical applications. Dr. Xu has published extensively in top venues including SIGGRAPH (with two 2024 Best Paper Honorable Mentions), CVPR, TPAMI, and IJCV. In 2024 alone, he had 3 papers at SIGGRAPH Asia, 1 at TPAMI, 3 at ACMMM, 7 at SIGGRAPH, 1 at IJCV, and 9 at CVPR. Best Paper Honorable Mention at SIGGRAPH 2024 (CLAY) Best Paper Honorable Mention at SIGGRAPH 2024 (DressCode) His research group develops cutting-edge technologies for human performance capture and 3D scene understanding, with projects like UnstructuredFusion for real-time 4D reconstruction, EventCap for high-speed motion capture, and FlyFusion for volumetric capture using flying cameras. They focus on practical applications in virtual reality, augmented reality, telepresence, and digital content creation.

Youngjoong Kwonمشاهده پروفایل

استادیار

• Computer Vision
• Computer Graphics
• Human Performance Capture
• +۳ مورد دیگر

Youngjoong Kwon is an incoming Assistant Professor in the Department of Computer Science at Emory University (Fall 2025), with postdoctoral research experience at Stanford University's Translational AI Lab and Vision and Learning Lab, and Carnegie Mellon University's Robotics Institute. He holds a PhD in Computer Science from the University of North Carolina at Chapel Hill and a BS from Yonsei University, Korea. Education: PhD, Computer Science, University of North Carolina at Chapel Hill (2023) BS, Computer Science, Yonsei University (2017) Research: His work bridges Computer Vision and Computer Graphics, focusing on human performance capture, avatar modeling, neural rendering, and telepresence systems. Recent publications demonstrate expertise in sparse view synthesis, deformable light fields, and real-time 3D avatar generation. Awards: Bronze Prize, 27th HumanTech Paper Award, Samsung Electronics Co., Ltd. (2022) Academic Engagement: Active as Area Chair (3DV 2026) and reviewer for top conferences (CVPR, ECCV, NeurIPS, etc.) and journals. Collaborations: Hosted by institutions including University of British Columbia, Max Planck Institute for Intelligent Systems, Stanford University, Adobe Research, NVIDIA Research, Texas A&M University, and Brown University for invited talks.

Feng Xuمشاهده پروفایل

دانشیار

• 3D Vision
• Computer Graphics
• Digital Health
• +۴ مورد دیگر

Feng Xu is an Associate Professor at the School of Software, Tsinghua University, Beijing, China. His research bridges computer science , medicine , and neuroscience , focusing on interdisciplinary applications in 3D vision, digital health, and human motion capture. Education : Ph.D. in Automation (2007-2012) and B.S. in Physics (2003-2007), both from Tsinghua University. Research Interests : 3D Vision, Computer Graphics, Digital Health, Physics-based Modeling, and Real-time Human Motion Tracking. His work explores 3D vision and graphics through applications like IMU-based motion capture , NeRF editing , and facial geometry reconstruction . Recent publications emphasize integrating physics-aware models with deep learning for real-time performance, particularly in healthcare contexts such as mediastinal neoplasm diagnosis and radiology report generation . Notable contributions include the EditableNeRF framework for topology editing and Transformer IMU Calibrator for dynamic sensor calibration. His work has received the Best Student Paper Award at IEEE ICME 2019 . Contact : Email: xufeng2003@gmail.com Email: feng-xu@tsinghua.edu.cn

Congyi Zhangمشاهده پروفایل

پژوهشگر ارشد

• Computer Science
• Neural Shape Representation
• 3D Reconstruction
• +۳ مورد دیگر

Congyi Zhang is a postdoctoral research and teaching fellow in the Department of Computer Science at the University of British Columbia. He earned his Ph.D. in Computer Science from Peking University and a B.Sc. in Mathematics from Fudan University. Prior to his current role, he served as a research associate at the Department of Computer Science, Hong Kong University, and as a visiting researcher at the Max Planck Institute for Informatics. His research focuses on neural shape representation, AI-driven 3D content generation, human-computer interaction, and 3D reconstruction techniques. He has contributed to methods that improve geometric accuracy, optimize sampling strategies, and enable efficient local editing of 3D models. Recent publications highlight advancements in neural implicit fields, multiview diffusion models, and efficient 3D mesh creation from 2D inputs. His work balances theoretical innovation with practical applications in digital media, orthodontics, and archaeology. He is currently transitioning to an Assistant Professor position at the Computer Science Department, University of Texas at Dallas, where he seeks motivated Ph.D. students for Spring/Fall 2026 cohorts.

Xudong Xuمشاهده پروفایل

پژوهشگر

• Embodied AI
• 3D Scene Generation
• Generative Modeling
• +۳ مورد دیگر

Xudong Xu is a researcher at Shanghai Artificial Intelligence Laboratory, specializing in Embodied AI with a focus on interactive scene generation and 3D object synthesis. He earned his Ph.D. in Information Engineering from The Chinese University of Hong Kong (2018-2023), advised by Prof. Dahua Lin, and holds a Bachelor's degree in Automation from Nanjing University (2014-2018), where he ranked first in his cohort. His research explores compositional scene generation, procedural modeling of articulated objects, and material-aware 3D synthesis. He has published in top venues like SIGGRAPH Asia, ECCV, NeurIPS, and contributed to projects such as MATLABER and RoomTex. His work leverages Gaussian splatting, PBR materials, and occupancy fields for high-fidelity 3D environments. Xudong has received prestigious awards including the Shanghai Leading Talent Program, CUHK Postgraduate Scholarship, and National Scholarship at Nanjing University. He serves as a reviewer for major AI/ML conferences like CVPR, ICCV, and NeurIPS, and mentors interns from institutions such as University of Virginia and UC San Diego.

Edith Tretschkمشاهده پروفایل

پژوهشگر

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

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

Bastian Wandtمشاهده پروفایل

پژوهشگر

• Human Motion Capture
• 3D Reconstruction
• Machine Learning
• +۳ مورد دیگر

Bastian Wandt is a Researcher at the University of British Columbia in the group of Helge Rhodin, and will join Linköping University as an Assistant Professor in September 2022. He holds a PhD from Leibniz University Hannover (2015–2020) and a Mechatronics degree (B.Sc. 2012, M.Sc. 2015) from the same institution. His research focuses on human motion capture, 3D reconstruction, and machine learning, particularly deep learning techniques for weakly supervised training and probabilistic modeling. He founded the AI consulting company HEUWA in 2018 and has taught courses such as DATA 311 at UBC. Research interests include applying neural networks and dimensionality reduction to human pose estimation, with special emphasis on monocular video analysis and physics-based models. Key contributions involve unsupervised learning methods like ElePose and CanonPose , as well as anomaly detection frameworks like Same Same But DifferNet . Awards include the KI Talent Award (2020, €4,000) for his dissertation. He has supervised numerous theses on topics like pose space modeling, recurrent neural networks for motion capture, and texture synthesis. His work bridges computer vision, robotics, and medical imaging applications.

Mario Zellerمشاهده پروفایل

مدرس

• Virtual Reality
• 3D Graphics
• Media Production
• +۳ مورد دیگر

FH-Prof. Dipl.-Ing. (FH) Mario Zeller is a Lecturer at the University of Applied Sciences St. Pölten, affiliated with the Department of Media and Digital Technologies and the Institute of Creative Media Technologies. He teaches in programs including Digital Media Technologies (MA), Digital Design (MA), and Media Technology (BA). His career began with studies in Telecommunications and Media at the same institution, followed by an ORF graphics department internship (2003-2004). Since 2004, he has worked as a post-production freelancer and in real-time 3D on-air graphics at ORF. His research focuses on virtual reality, 3D graphics, and interactive media, with notable projects like the VRinMotion series and Virtual Studio Production initiatives. Key projects include the VRinMotion trilogy exploring immersive motion-based experiences and the 2010 study on virtual studio training systems. He actively contributes to media education through teaching and projects like 'Meta VFX' and 'Unreal Engine Applications.' His work bridges academic research and industry applications in digital media and interactive technologies.

• Construction Simulation
• Discrete-Event Simulation
• 3D Visualization in Construction
• +۴ مورد دیگر

Dr. Julio Martinez is a Professor of Civil Engineering at Purdue University's College of Engineering. His research focuses on advanced simulation techniques, 3D visualization for construction processes, and optimization of earthwork operations. He has pioneered methodologies for integrating discrete-event simulation with virtual reality and augmented reality technologies to enhance construction planning and risk management. His work emphasizes sustainable construction practices, dynamic resource allocation, and real-time user interaction in simulation systems. Notable contributions include developing the STROBOSCOPE simulation framework and the VITASCOPE visualization toolkit. He has authored over 50 papers on topics ranging from stochastic modeling to scalable scene rendering algorithms. Dr. Martinez’s research bridges engineering and computer science, applying cutting-edge visualization techniques to traditional construction challenges. His recent work explores the integration of wireless communication simulations in earthmoving operations and the validation of complex construction models through immersive visualizations. His publications consistently address practical construction scenarios, with a focus on improving operational efficiency and safety through advanced modeling and simulation approaches. Current research trends include enhancing simulation scalability, improving 3D animation realism, and applying simulation for sustainable infrastructure development.

Tim McGrawمشاهده پروفایل

دانشیار

• Virtual Reality
• Scientific Visualization
• Real-Time Computer Graphics
• +۲ مورد دیگر

Tim McGraw is an Associate Professor in the Department of Computer Graphics Technology at Purdue University’s Purdue Polytechnic Institute. He specializes in virtual reality, scientific visualization, and medical image processing, with notable work on diffusion tensor MRI (DT-MRI) visualization and mesh editing in VR. He has held industry roles as a Mechanical Engineer and game developer at Electronic Arts, Schell Games, and Rainbow Studios. Education: Ph.D. in Computer and Information Science and Engineering (University of Florida), B.S. in Mechanical Engineering (University of Florida). Research interests focus on blending computational art with scientific challenges, including real-time graphics, medical imaging, and game development. His recent work explores soft-body physics simulation (e.g., Mesh Mortal Kombat) and thermal imaging analysis. Awards include 2024 Best Paper/Presentation at Motion Interaction Games and 2024 SIGGRAPH Best in Show. Grants include 3D Visualization of Molecular Dissolution (2016) and industry partnerships with NVIDIA, Eli Lilly, and Boeing. He holds four patents related to DT-MRI visualization technologies developed with Siemens Corporate Research. Labs/Teams: Leads the Interactive Graphics Technology Lab, contributing to projects like Bodygraphe (a gestural computing art installation showcased at SIGGRAPH 2016).

• Computer Graphics
• Computer Vision
• Machine Learning
• +۹ مورد دیگر

Corey Toler-Franklin is an Assistant Professor in the Computer Science Department at Barnard College, Columbia University, and Director of the Graphics, Imaging & Light Measurement Lab (GILMLab). Her research focuses on computer graphics, vision, and AI applications in biomedical research, archaeology, and cultural heritage preservation. She holds a Ph.D. in Computer Science from Princeton University and has held academic roles at the University of Florida and industry positions at Autodesk, Adobe, and Google. Her educational background includes a B.Arch. from Cornell University and an M.S. in Computer Graphics from Cornell’s Program of Computer Graphics. Notable awards include the 2009 Google Anita Borg Award and recognition as the first African American to earn a Ph.D. in CS from Princeton. Her work bridges computational methods with real-world applications in healthcare and cultural preservation, including AI for cancer diagnosis and 3D digitization of fossils. Publications highlight innovations in multispectral rendering, material style transfer, and medical imaging analysis. Collaborations span oncology, neuroscience, and archaeological institutions like the Akrotiri Laboratory. The GILM Lab emphasizes interdisciplinary projects such as the iDigFossils initiative, engaging K-12 students in STEM through 3D printing and exploration of fossils.

Yaoyao Liuمشاهده پروفایل

استادیار

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

Yaoyao Liu is an Assistant Professor at the University of Illinois Urbana-Champaign, holding joint appointments in the School of Information Sciences and Coordinated Science Laboratory. He is affiliated with the Siebel School of Computing and Data Science, National Center for Supercomputing Applications (NCSA), and Illinois Informatics. His research focuses on computer vision and machine learning, particularly in areas like continual learning, few-shot learning, and 3D geometry modeling. He completed his PhD at the Max Planck Institute for Informatics and a BS at Tianjin University. Research Interests: Continual learning and class-incremental learning Generative models and diffusion models 3D geometry and medical imaging applications Awards: ECVA PhD Award (2024). Professional Activities: Area Chair for CVPR, NeurIPS, ICLR, and other top conferences. Served as Senior Program Committee member for AAAI and IJCAI. Labs/Teams: Active in interdisciplinary projects at NCSA and Illinois Informatics, collaborating on medical imaging and 3D vision challenges.

Huy Voمشاهده پروفایل

دانشیار

• Big Data Systems
• Data Science
• High-Performance Computing
• +۳ مورد دیگر

Huy Vo is an Associate Professor in the Department of Computer Science at the City College of New York (CCNY), part of the City University of New York (CUNY) system. His research focuses on Big Data Systems, Data Science, High-Performance Computing, Large-Scale Visualization, and Scalable Display Building. He is affiliated with CCNY's School of Engineering and maintains an active website at https://www-cs.ccny.cuny.edu/~hvo/ . His work spans urban analytics, visualization technologies, and machine learning applications. Notable contributions include analyzing global urban road networks using GNNs, developing semiconductor-specific large language models (SemiKong), and optimizing fleet management for ride-pooling in NYC. He also explores public health technologies, such as asthma self-management apps and pandemic policy impact visualizations. Vo's research often integrates interdisciplinary approaches, combining geospatial data, computational modeling, and real-time systems. His recent work highlights trends in scalable computing, AR visualization, and data-driven decision-making in urban environments. No scientific awards are explicitly mentioned in the provided text. His advising and grants sections remain unspecified, but his extensive publication record indicates active research collaborations and grant-funded projects. The SAT-Hub project exemplifies his focus on smart urban infrastructure, while his work on visualization frameworks like Unitypic underscores innovations in interactive 3D systems.

• Virtual Design
• Systemic Design
• Computer Graphics
• +۳ مورد دیگر

Luca Porru serves as an External Lecturer at Polytechnic University of Turin, holding dual appointments in the Department of Architecture and Design (DAD) and Department of Control and Computer Science (DAUIN). He has consistently taught design-focused courses since the 2019/2020 academic year through the upcoming 2025/2026 term within the College of Architecture and Design. His academic expertise centers on digital design methodologies with emphasis on: Virtual Design and Virtual Set construction Systemic Design frameworks Computer Graphics and Rendering techniques 3D Modeling and Shape Geometry Design Communication through Digital Media Virtual Reality applications in design education Porru delivers specialized instruction across Bachelor's and Master's programs, notably teaching Virtual Design modules for Systemic Design courses alongside core instruction in Modeling Design, Design Representation, and Storytelling/Virtual Animation within the Design and Communication curriculum.

• Computer Graphics
• 3D Modeling
• Computer Animation
• +۷ مورد دیگر

Marie-Paule Cani is a Professor of Computer Science at École Polytechnique (Institut Polytechnique de Paris), where she serves as Dean of the Master of Science and Technology program and leads the STREAM research team at LIX Laboratory (CNRS/IP Paris). Her research bridges computer graphics, HCI, and AI, focusing on expressive 3D modeling, animation, and virtual environments. Education: 1987: M.Sc. in Computer Science, École Normale Supérieure & University Paris XI 1990: Ph.D. in Computer Graphics, University Paris XI 1995: Habilitation in Computer Science, Institut National Polytechnique de Grenoble Research Interests: She pioneers user-centered tools for 3D content creation, combining gesture-based interfaces (sketching, sculpting) with knowledge-enhanced procedural models. Key areas include implicit surfaces, physical simulation, AI-driven animation, and accessible tools for non-experts. Her work enables intuitive design of complex shapes, terrains, and dynamic scenes. Publication Trends: Recent work (2023–2025) emphasizes AI-integrated graphics, including controllable natural phenomena (volcanoes, erosion), sketch-based bio-visualization, reinforcement learning for animation, and real-time character control. Cross-disciplinary applications span geology, biology, and cinematography. Awards & Honors: ACM Steven A. Coons Award (2023) French Academy of Sciences (2020) ACM SIGGRAPH Academy (2019) ERC Advanced Grant EXPRESSIVE (2012–2017) CNRS Silver Medal (2012) Leadership & Grants: She founded research teams (STREAM, Imagine, Evasion) and secured major funding: ERC Advanced Grant, Google-École Polytechnique AI Chair (2018–2021), Horizon 2020 project CLIPE (2020–2024), and Hi!Paris Creative AI Fellowship (2021–2024). She mentors researchers in geometric modeling, animation, and AI. Labs & Teams: Directs the Modeling, Simulation & Learning pole at LIX (2019–2023). Founded STREAM (Structure Representation for Animation/Modeling) and Imagine (Inria/Grenoble teams), advancing real-time graphics and procedural content.