جست‌وجوی استاد و پژوهشگر

Pierre Bénardمشاهده پروفایل

دانشیار

• Computer Graphics
• Image Synthesis
• 3D Modeling
• +۳ مورد دیگر

Pierre Bénard serves as an Associate Professor at the University of Bordeaux, conducting research with the manao team at LaBRI (CNRS, Inria). His academic career spans teaching and research in computer graphics with notable industry experience at Pixar Research Group and academic work at the University of Toronto. Dr. Bénard earned his PhD from the MSTII Doctoral School of Université de Grenoble in July 2011 under the supervision of Joëlle Thollot and François Sillion at Laboratoire Jean Kuntzmann. His educational background forms the foundation for his expertise in graphics systems and visualization techniques. His research focuses on computer graphics with specializations in image synthesis, 3D modeling, and animation techniques. His work bridges theoretical computer graphics with practical implementation, particularly evident in his teaching of OpenGL-based rendering systems and shader programming. His research interests encompass visual effects creation, non-linear animation techniques, and real-time graphics programming for multimedia applications. As an educator, Dr. Bénard teaches advanced courses including Advanced Image Synthesis (M2), 3D Worlds (M1), and C++ Programming for Multimedia. His teaching philosophy emphasizes hands-on implementation of graphics concepts using modern OpenGL frameworks and C++ programming techniques. His course materials demonstrate a commitment to teaching object-oriented programming principles through practical graphics applications. Dr. Bénard leads research activities within the manao team at LaBRI, focusing on innovative graphics techniques and visual effects. His industry experience at Pixar complements his academic work, providing practical insights into production-level graphics systems. His research environment fosters collaboration between academic theory and industry application in the computer graphics domain.

Thomas Engelhardtمشاهده پروفایل

پژوهشگر

• Real-Time Rendering
• Global Illumination
• 3D Graphics
• +۴ مورد دیگر

Thomas Engelhardt is a Researcher and PhD student at the Computer Graphics Group of the Karlsruhe Institute of Technology (KIT) , Germany. His work focuses on real-time rendering techniques, including global illumination, participating media, and visibility culling. Research Interests: Interactive 3D graphics High-quality lighting simulation GPU-based rendering algorithms Occlusion culling and visibility optimization Participating media rendering Environment mapping techniques Publications demonstrate expertise in virtual point lights, epipolar sampling, hierarchical buffers, and scalable final gathering for global illumination.

David Vanderhaegheمشاهده پروفایل

دانشیار

• Computer Graphics
• Rendering
• Expressive Rendering
• +۵ مورد دیگر

David Vanderhaeghe is an Associate Professor at Université de Toulouse , affiliated with the IRIT laboratory and co-founder/CSO of RollingDot . He leads the STORM team since 2021. Research Interests : Computer Graphics Rendering (Realtime & Offline) Expressive Rendering & Stylization of Animated Scenes User Control in 3D Rendering Geometry Processing Color Point-Clouds Scientific Awards : Best Paper (3rd, jFIG 2021) Public Award, jFig 2020 ShaderToy Contest CRCT Sabbatical (2019) PEDR (Doctoral Supervision Premium, 2018-2022, 2014-2017) Best Paper (AFIG 2014, Eurographics 2011, AFIG 2006) Honorable Mention in Rendering (NPAR 2011) Advising and Grants : Supervised PhD students like Nicolas Barroso and Thomas Subileau, co-led projects funded by ANR (Structures, CaLiTrOp), and participated in European and national grants. Labs and Teams : Head of the STORM team at IRIT, involved in computer graphics research.

Manolis Sangriotisمشاهده پروفایل

دانشیار

• Image Processing
• Computer Vision
• Stereo Image Coding
• +۴ مورد دیگر

Manolis Sangriotis is an Associate Professor at the National and Kapodistrian University of Athens, affiliated with the Department of Informatics and Telecommunications. His academic journey began with a B.Sc. in Physics (1970), followed by M.Sc. degrees in Electronics and Radioelectrology (1973) and Electronic Automation (1975), culminating in a Ph.D. in Informatics and Telecommunications (1980) from the University of Athens. His research focuses on image processing , computer vision , and 3D imaging , with emphasis on stereo image coding, integral photography, and real-time compression architectures. He explores applications in medical imaging, autostereoscopic displays, and multimedia systems, leveraging wavelet transforms, morphological operations, and statistical clustering. Recent publications (2012–2004) reveal a strong trend toward integral imaging innovations , including rectification frameworks, watermarking, and 3D-DCT compression. His work consistently addresses challenges in multiview data representation, disparity estimation, and photorealistic rendering, bridging computer vision with optical engineering. Scientific Awards: Best Paper Award at IEEE 8th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (2012) He actively advises PhD students, including Eirini Kostopoulou, Tzanoukos Georgios, and Papageorgiou Louis. His research group collaborates on projects related to real-time systems and image datasets, often supported by institutional grants. As part of the RTSImage laboratory, he contributes to developing computational tools for image analysis and compression, with applications spanning medical diagnostics and 3D display technologies. Future directions include advancing omnidirectional imaging and robustness in automated biomedical assessments.

Jonas Ungerمشاهده پروفایل

استاد

• Computer Graphics
• Image Processing
• Artificial Intelligence
• +۳ مورد دیگر

Jonas Unger is a Professor at Linköping University's Department of Engineering and Natural Sciences (ITN) and Media and Information Technology (MIT). As a research leader in computer graphics and image processing, he contributes to advanced visualization techniques, GPU computing, and AI applications in healthcare and climate adaptation. Specializes in BRDF modeling, spectral light field imaging, and augmented intelligence Active in AI4Climateadaptation and Wallenberg Autonomous Systems Program (WASP) Recipient of the 2023 Chester Carlson Research Prize Develops AI methods for medical imaging (SCAPIS dataset) and autonomous systems His recent work focuses on deep learning for material acquisition, real-time rendering optimizations, and visual analytics pipelines for disaster response systems. Current projects include multi-agent reinforcement learning for air traffic control and GPU-accelerated signal processing techniques. Scientific awards include: Chester Carlson Research Prize (2023) He collaborates with Visual Sweden's Augmented Intelligence platform, co-leads major visualization conferences, and contributes to Horizon 2020 Marie Skłodowska-Curie funded research. Contact: jonas.unger@liu.se

• Artificial Intelligence
• Computer Vision
• Domain Adaptation
• +۶ مورد دیگر

Tatiana Tommasi is an Associate Professor at the Department of Control and Computer Science (DAUIN) at Polytechnic University of Turin, actively contributing to advanced AI research and education. She serves as Deputy Coordinator of the National Doctoral College in Artificial Intelligence and Scientific Advisor for the European AI, Data, and Robotics Association (ADRA) and ELLIS Network. Her affiliations include the SmartData@PoliTO Laboratory and VANDAL Visual and Multimodal Applied Learning Laboratory. Her research focuses on algorithm fairness, computer vision, domain adaptation, autonomous driving, and robot learning. Recent work includes improving neural network reliability through fault-aware design, 3D semantic novelty detection, and visual relationship reasoning for robotic grasp planning. She has contributed to European research projects like ELSA (Secure and Safe AI) and commercial initiatives in space technologies and autonomous vehicle uncertainty quantification. Selected 2024-2025 publications demonstrate expertise in foundation models, fairness metrics, uncertainty estimation, and geometric deep learning. Her team leads commercial research projects on industrial robotics trajectory generation and satellite data analysis. She teaches core courses in Computer Engineering, Automotive Engineering, and Data Science, mentoring PhD students in Artificial Intelligence and Computer Systems Engineering. Research keywords: Artificial Intelligence, Machine Learning, Computer Vision, Domain Adaptation, Robot Learning, Transfer Learning, Fairness in AI, Uncertainty Quantification, Autonomous Driving, 3D Point Cloud Analysis, Vision Transformers, Industrial Robotics.

Kevin Desaiمشاهده پروفایل

استادیار

• Computer Vision
• Virtual/Augmented/Mixed Realities
• Collaborative Virtual Environments
• +۳ مورد دیگر

Dr. Kevin Desai is an Assistant Professor in the Department of Computer Science at The University of Texas at San Antonio (UTSA), affiliated with the College of Sciences. He leads the Vision & Immersive Realities Lab (VIRLab), part of the School of Data Science. His research focuses on collaborative virtual environments, computer vision, and immersive technologies for healthcare and telehealth applications. Dr. Desai holds a Ph.D. and M.S. in Computer Science from the University of Texas at Dallas, and a B.Tech. in Computer Science and Engineering from Nirma University. His work bridges computer science with human-centered design, emphasizing real-world applications like tele-rehabilitation and autism support systems. His research interests include virtual/augmented/mixed reality systems, 3D pose estimation, and AI-driven health monitoring. Notable contributions include the HR-STAN framework (Best Paper Award, CVPR 2022), which predicts cybersickness using multimodal sensor fusion, and the Virtepex tele-physical exam system. Dr. Desai advises students such as Mushfiq Riaz, Ayda, and Omar Medjaouri in projects spanning VR/AR applications, neural radiance fields, and low-latency DNN frameworks. He actively collaborates with industry partners like Alienware and Lambda Labs, as evidenced by VIRLab's equipment and conference presentations at CVPR 2024. His lab explores cutting-edge technologies including 3D human modeling (TE-NeRF), energy-efficient AI (EncodeNet), and personalized cybersickness prediction algorithms. Recent work addresses exergames for post-stroke rehabilitation and multimodal healthcare streaming systems.

• Federated Learning
• Privacy-Preserving Machine Learning
• Distributed Deep Learning
• +۴ مورد دیگر

Praneeth Vepakomma is an active researcher in the field of machine learning with a strong publication record spanning from 2015 to the present. His work primarily focuses on privacy-preserving distributed learning systems, with particular emphasis on federated learning, split learning, and techniques for maintaining data privacy while enabling collaborative AI development. His research interests center around developing efficient and privacy-preserving machine learning frameworks. Vepakomma has made significant contributions to federated learning optimization, split learning architectures, and differential privacy techniques for deep learning systems. His recent work has increasingly focused on adapting these techniques for large language models, addressing communication efficiency challenges and privacy concerns in distributed fine-tuning scenarios. Analysis of his publication trends reveals a clear trajectory from foundational work in privacy-preserving machine learning (2015-2019) to increasingly sophisticated approaches for distributed learning systems (2020-2025). His recent publications demonstrate a strong focus on solving practical challenges in federated and split learning for large language models, with particular attention to communication efficiency, privacy guarantees, and architectural innovations for heterogeneous environments. Vepakomma has established a robust collaborative network, most notably with Ramesh Raskar (50+ co-authored papers), indicating a long-standing research partnership. His work bridges theoretical foundations with practical implementations, making significant contributions to the advancement of privacy-preserving distributed machine learning.

Igor Gilitschenskiمشاهده پروفایل

استادیار

• Robotics
• Computer Vision
• Deep Learning
• +۳ مورد دیگر

Igor Gilitschenski is an Assistant Professor in Computer Science at the University of Toronto, leading the Toronto Intelligent Systems Lab (TISL). He focuses on developing probabilistic and learning-based techniques for robotic perception and decision-making, aiming to enable robust interactive autonomy. Prior to this, he held roles at MIT CSAIL, ETH Zurich's Autonomous Systems Lab, and the Karlsruhe Institute of Technology (KIT). His research interests include autonomous systems, computer vision, and deep learning applied to robotics. He collaborates with institutions like the Vector Institute and is a Vector Research Scholar. His work spans robot learning, simulation-driven policy training, and safety-critical systems. Notable projects include pseudo-simulation for autonomous driving, vision-language-action models, and neural radiance fields for 3D scene representation. He actively recruits PhD students to work at the intersection of computer vision, deep learning, and robotics, emphasizing controllable simulation engines and safe learning frameworks. Recent research trends in his articles highlight advancements in generative models, reinforcement learning, and perception systems for dynamic environments. He emphasizes collaboration across disciplines, including event-based vision and language-guided reasoning for robotic tasks.

Tobias Isenbergمشاهده پروفایل

پژوهشگر

• Scientific Visualization
• Computer Graphics
• Human-Computer Interaction
• +۵ مورد دیگر

Tobias Isenberg is a Senior Research Scientist (Directeur de recherche) at Inria's AVIZ project group in Saclay, Université Paris-Saclay. He is affiliated with the Johann Bernoulli Institute for Mathematics and Computer Science at the University of Groningen, Netherlands. His research focuses on interactive scientific visualization, illustrative rendering techniques, and human-computer interaction in non-traditional environments like AR/VR. He has pioneered methods for blending dynamic data physicalizations with virtual content and enhancing collaborative AR learning. Key contributions include machine learning-driven visualization tools for cell lineage analysis and perceptually grounded evaluation frameworks for visualizations. His work spans medical visualization, educational AR systems, and reproducibility in visualization research. He has collaborated with institutions such as the Interactive Media Lab Dresden and led projects like Naviscope (Inria) and tVISt (ANR/DFG). Recent awards include the 2024 SciVis Test-of-Time Award for his 2012 selection techniques paper and a Best Paper Award at CHI 2025 for AR transition techniques. He currently seeks a PhD student to advance interactive 3D dataset exploration methods. Notable grants include the tVISt collaboration grant (2024) and institutional funding from Inria. His lab, AVIZ, develops open-source tools like LineageD+ for biological data analysis and interactive physicalization systems. Recent publications emphasize cross-reality visualization, human-AI collaboration, and reproducibility in visualization research.

Karan Sher Singhمشاهده پروفایل

استاد

• Computer Graphics
• Human-Computer Interaction (HCI)
• Artificial Intelligence
• +۴ مورد دیگر

Karan Sher Singh is a Professor in the Department of Computer Science at the University of Toronto, affiliated with the Dynamic Graphics Project (DGP) laboratory. His research focuses on interactive computer graphics, human-computer interaction, and artificial intelligence, with applications in sketch-based interfaces, character animation, and immersive technologies like AR/VR. He has pioneered tools such as Meshmixer, CrossShade, and JALI Research, which have been adopted in industries including film (e.g., Weta Digital’s Avatar: The Way of Water) and gaming (Cyberpunk 2077). Education and Background: Completed his PhD in 1994, working on early virtual teleconferencing systems at ATR. His work bridges artistic expression, technical innovation, and perceptual principles to create intuitive design tools. Research Interests: Sketch and sculpt interfaces for 3D modeling and design Facial and character animation (INCA) for films and games Mathematical surface representations for conceptual design Augmented/VR storytelling and immersive environments (e.g., JanusXR) Artistic projection and non-photorealistic rendering Recent Work Trends: Articles from 2016–2023 emphasize VR/AR interaction, immersive design tools, and anatomically based animation. His research often integrates HCI principles with geometric algorithms to address challenges in freehand sketching, mid-air gestures, and musculoskeletal modeling. Awards and Recognitions: Best Paper Awards at SBIM (2008, 2012, 2014) Technology Transfer Awards from MITACS NCE (2003–2012) VFX Oscar-winning contribution via Weta Digital Advising and Industry: Supervised over 20 graduate students, many contributing to tech companies like Pixar, Google, and EA. Co-founded JALI Research, JanusVR, and collaborated with industry leaders such as SideFX, NVIDIA, and NVIDIA. Labs and Teams: Leads the DGP lab, fostering cross-disciplinary projects between academia and industry. Active in developing open-source tools like JanusXR and Meshmixer.

• Computer Graphics
• Machine Vision
• Artificial Intelligence
• +۵ مورد دیگر

Dr Farshad Einabadi is a Senior Research Engineer at the Centre for Vision, Speech and Signal Processing (CVSSP) , University of Surrey, and contributes to the CoSTAR National Laboratory . His work focuses on neural rendering, real-time systems, and media personalization within the intersection of computer graphics, machine vision, and AI. Research interests include lighting/illumination applications (acquisition, modeling, rendering), virtual production tools, and industrial sensor calibration. He leads projects in next-gen UK screen technologies infrastructure (UKRI AHRC CoSTAR) and has contributed to EPSRC AI4ME and EU FP7 Dreamspace initiatives. Publications emphasize datasets like ForecasterFlexOBM (multi-view audio-visual) and 3DVHshadow , advancing human avatar rendering and cast shadow generation. He teaches AI Bootcamp for the UKRI CDT in Digital Media Inclusion and reviews for Eurographics and top-tier conferences. Industry experience includes software engineering for real-time augmented reality systems. Collaborates in labs/teams at CVSSP and CoSTAR, advancing projects in virtual production and immersive media technologies.

Patric Ljungمشاهده پروفایل

دانشیار

• Visualization Technologies
• Software Design
• Medical Imaging
• +۴ مورد دیگر

Patric Ljung is an Associate Professor at Linköping University, affiliated with the Media and Information Technology (MIT) division within the Department of Science and Technology (ITN). He leads the Immersive Visualization group and has been a key figure in research projects focusing on visualization technologies, software design, and medical imaging applications. Previously, he worked at Siemens Corporation in the U.S., contributing to medical visualization tools and quality management. Dr. Ljung holds an M.S. in Information Technology (2000) and a Ph.D. in Scientific Visualization (2006) from Linköping University. His research focuses on large-scale visualization technologies, software architecture for visualization systems, and direct volume rendering. Current projects explore heterogeneous data management, data provenance, and unification of transfer functions. He emphasizes immersive visualization techniques for applications in healthcare, planetary science, and public engagement through collaborations with institutions like the Visualization Center C. With over 40 peer-reviewed publications and seven patents, his work spans medical visualization, augmented reality, and interactive systems. Recent trends include leveraging immersive technologies for climate change communication and autonomous systems visualization. He has directed projects such as C-research, coordinating visualization efforts with the Visualization Center C. His leadership includes roles as head of the Immersive Visualization group and former director of C-research. Collaborations with Siemens and the Visualization Center C highlight his interdisciplinary approach.

• Machine Learning
• Renewable Energy
• Quantum Computing
• +۵ مورد دیگر

Dr. Hao Chen is an Assistant Professor at the University of Twente, affiliated with the Industrial Engineering & Business Information Systems department and the MESA+ Institute. His research focuses on renewable energy systems, machine learning applications, and autonomous systems, contributing to the United Nations Sustainable Development Goals. Dr. Chen's research interests include wind energy modeling, quantum computing for energy systems, vehicular edge computing, and trajectory prediction in autonomous driving. He explores machine learning techniques for fault detection in energy infrastructure and develops innovative solutions for sustainable energy scenarios. His work also addresses human-machine interaction in autonomous vehicles and environmental monitoring systems. His recent publications explore advancements in computer vision techniques for scene graph prediction, building outline extraction, and camera pose estimation. He has also contributed to studies on energy systems, including wind model downscaling, quantum computing applications, and cost-efficient vehicular edge computing for air pollution monitoring. His work bridges theoretical developments with practical applications in sustainable energy and autonomous technologies. No scientific awards or advising/grant information is available. His research aligns with the university's focus on sustainable innovation and technological solutions.

Manmohan Chandrakerمشاهده پروفایل

استاد

• Computer Vision
• 3D Reconstruction
• Scene Understanding
• +۵ مورد دیگر

Manmohan Chandraker is a Professor in the Department of Computer Science & Engineering at the University of California, San Diego (UCSD). His research focuses on computer vision, 3D reconstruction, and autonomous driving, with interdisciplinary links to robotics, machine learning, and computer graphics. He leads projects in 3D scene understanding, real-time visual odometry, and sensor fusion for autonomous systems. His work has been recognized with top academic awards and industry accolades. Education: B.Tech. in Electrical Engineering from IIT Bombay Ph.D. in Computer Science from UCSD Postdoctoral scholarship at UC Berkeley Research Interests: Chandraker’s work addresses challenges in 3D reconstruction under complex lighting and materials, autonomous driving systems, and physically-based inverse rendering. Key contributions include frameworks for non-convex optimization in geometric reconstruction and semantic-driven dense reconstruction techniques. His research bridges theory and practice, with applications in augmented reality, robotics navigation, and automotive safety systems. Key Awards: Best Paper Award at CVPR 2014 UCSD CSE Dissertation Award (2009) NEC Business Contribution Award (2015) Advising & Industry Collaboration: He has led teams at NEC Labs America, collaborating with automobile manufacturers to develop single-camera systems for real-time autonomous driving. His work on closed-loop traffic simulations and adversarial scenario generation has driven industry partnerships and patents. Current research explores multimodal LLM integration, data-centric AI tools (e.g., Ymir platform), and photorealistic scene synthesis. Labs & Projects: Chandraker’s group develops open frameworks like OpenRooms and TRoVE for 3D scene datasets, and contributes to benchmarks for domain adaptation in vision tasks. His team also works on safety-critical systems for autonomous vehicles through projects like SAFE-SIM and Drive-1-to-3.