Philipp Erler is a PreDoc Researcher at the Computer Graphics department of Vienna University of Technology . His work focuses on surface reconstruction from point clouds, geometry processing, and deep learning applications in computer graphics. Research Highlights : LidarScout (2025): Direct out-of-core rendering of massive point clouds PPSurf (2024): Patch-based deep learning for surface reconstruction Points2Surf (2020): Implicit surface learning from raw point clouds without normals His research extends into virtual reality, physical simulations, and natural language processing. He has supervised four theses on topics including surface reconstruction optimization and differentiable rendering.
Christian Freude is a PreDoc Researcher at the Department of Computer Graphics , Faculty of Informatics , Vienna University of Technology (TU Wien) , focusing on Visual Computing and Human-Centered Technology . His work bridges photorealistic rendering , Monte Carlo methods , and real-time simulation . Active in projects: Toward Optimal Path Guiding (2023–2027, WWTF-funded), ACD (2020–2028) Supervised PhD/Master's students : Lukas Lipp, Christian Jauernik, Johannes Lurf Research spans Monte Carlo denoising , radiative thermal transport , subsurface scattering , and point cloud rendering . His 2025 work on Inverse Simulation of Radiative Thermal Transport introduces novel methods for efficient heat distribution modeling. Key scientific awards include the OCG Förderpreis 2016 . Publications from 2015–2025 highlight advancements in rendering algorithms , stereoscopic film , and uncertainty visualization .
Bernhard Kerbl is a Post-doctoral Researcher at the Computer Graphics Group (E193-02) within the Faculty of Informatics at Vienna University of Technology (TU Wien). He actively contributes to research in real-time rendering, GPU optimization, and 3D visualization. His work focuses on point cloud rendering, Gaussian splatting, and low-level graphics API development (particularly Vulkan). Core Research Areas: Real-time rendering, GPU programming, point cloud processing, 3D Gaussian splatting, task-based parallelism Projects: IVILPC (2023–2026), ACD (2020–2028), EVOCATION (2018–2022) Key Contributions: Developed real-time rendering techniques for massive datasets, pioneered GPU-based scene streaming architectures, and created novel methods for visual error prediction using machine learning. His work on Vulkan transition in academia received recognition, and he maintains active collaborations in GPU education. Scientific Achievements: Best Paper Award at EGPGV 2024 for "Fast Rendering of Parametric Objects on Modern GPUs" Recipient of Vienna Science and Technology Fund (WWTF) support for graphics research Technical Expertise: Specializes in CUDA, OpenGL/Vulkan APIs, and real-time systems. His work bridges academic research with practical implementations in virtual reality, augmented reality, and GPU education.
Pascal Guehl is a Part-Time Lecturer in Computer Graphics at the University of Strasbourg and Head of the new Master of Science and Technology in Extended Cinematography at École Polytechnique (LIX lab). He holds a PhD in Computer Graphics from the University of Strasbourg (2022) and has extensive experience in R&D roles across industry and academia. His core expertise spans procedural generation, real-time rendering, GPU computing, and virtual production technologies, with notable contributions to texture synthesis and semi-procedural modeling. Education highlights include a MRes from University Lyon 1 (2016), an Advanced Master from Arts & Métiers ParisTech (2005), and a master's in Physics from University Cergy-Pontoise (2000). His teaching spans over 15 years, covering C++ programming, real-time 3D graphics, and generative AI. Research focuses on interdisciplinary applications of computer graphics in film production, biology visualization, and defense systems. Key achievements include the semi-procedural texture synthesis framework (SIGGRAPH 2020) and leadership in ANR-funded projects like Animation Conductor (2023-2027). Awards include a Graphics Replicability Stamp and Honorable Mention for procedural texture work. Professional affiliations include ICube research lab (University of Strasbourg), where he co-supervises PhD students like Tara Butler, and collaborations with institutions like Telecom Paris, ENS Louis-Lumière, and Purdue University. Current projects emphasize extended cinematography tools and generative AI integration in visual effects pipelines.
Marcus A Brubaker is an Associate Professor of Computer Science at York University in Toronto and a Faculty Affiliate at the Vector Institute. He also serves as a Status-only Professor at the University of Toronto and conducts research consulting for Samsung AI Centre and Borealis AI in Toronto. His work focuses on interdisciplinary applications of machine learning, computer vision, and statistics, particularly in computational biology, medical imaging, and sensor systems. Brubaker's research interests include developing novel algorithms for 3D reconstruction (e.g., neural radiance fields), cryo-electron microscopy (Cryo-EM) analysis, noise modeling, and generative models. He has contributed significantly to methods like dynamic normalizing flows for stochastic processes, geometry-aware diffusion models, and text-guided image editing techniques. His work bridges theoretical machine learning with practical applications in bioimaging and computer graphics. His publications span over two decades, with recent trends emphasizing Bayesian methods, efficient neural network architectures, and multi-view scene understanding. Brubaker collaborates extensively with industry partners (e.g., Samsung AI) and academic institutions to advance AI-driven solutions in microscopy, image processing, and 3D modeling. Brubaker’s research has led to impactful tools like cryoSPARC for Cryo-EM structure determination and Wavelet Flow for high-resolution image analysis. He actively engages in academic outreach, as evidenced by his participation at ICCV2023 and mentorship of early-career researchers.
Ronan Boulic is a Professor at École Polytechnique Fédérale de Lausanne (EPFL) within the School of Computer and Communication Sciences . His work spans virtual reality, computer animation, and human-computer interaction. Key research themes: Virtual Reality, Embodied Cognition, Inverse Kinematics Recent focus: Cybersickness detection, Avatar embodiment, Biometric monitoring His 2025 publications include embodied body morphology tasks and standardized cybersickness assessment frameworks . Earlier works (2013-2018) explored haptic rendering , self-avatar perception , and real-time motion systems . Collaborators include Bruno Herbelin, Nana Tian, and Daniel Thalmann.
Hao Gao is a Professor in the Department of Computer and Information Science at the University of Macau, Faculty of Science and Technology. His research spans computer vision, image processing, and machine learning with a particular focus on human pose estimation, 3D reconstruction, and optimization algorithms. He maintains strong collaborative ties with Nanjing University of Posts and Telecommunications in China, reflecting a dual institutional affiliation that enhances his research impact across Greater China. His research interests center on computer vision and artificial intelligence, with significant contributions in human pose estimation, 3D reconstruction, point cloud processing, and optimization algorithms. Dr. Gao's work on skeleton-based action recognition, scene flow estimation, and neural rendering techniques has established him as a leading researcher in these specialized areas. His recent work on GaussianHead for high-fidelity head avatars and lifespan age synthesis demonstrates his ability to bridge theoretical advances with practical applications in digital human representation. Dr. Gao's publication record shows a clear evolution from foundational work on artificial bee colony algorithms to cutting-edge research in neural rendering and 3D vision. His recent publications (2023-2025) demonstrate a strong focus on human-centric computer vision problems, including pose estimation, motion prediction, and medical applications for Parkinson's disease assessment. The interdisciplinary nature of his work connects computer vision with healthcare applications, autonomous systems, and virtual reality. Dr. Gao has mentored numerous graduate students who have become productive researchers in their own right, including Haolun Li, Jiucheng Xie, and Jian Xiong who frequently appear as co-authors on his publications. His research group has secured funding for projects related to human motion analysis, medical image processing, and autonomous driving perception systems. His laboratory focuses on advancing computer vision techniques for human understanding, with recent projects including skeleton-based action recognition systems, Parkinson's disease assessment tools, and high-fidelity digital avatar creation. The team maintains strong industry connections, particularly in applications related to autonomous vehicles and medical diagnostics.
Dr. Eric Brachmann is a Researcher at Heidelberg University 's Visual Learning Lab (since 2017) and a Guest at Leibniz University Hannover (since 2019). He earned his Dr. rer. nat. in 2018 from TU Dresden (summa cum laude), preceded by a Diplom in media computer science (2012) and studies (2006–2012) at TU Dresden. Doctorate: TU Dresden (2018, summa cum laude) Diplom: TU Dresden (2012, passed with distinction) Education: Media and computer science (2006–2012) His research focuses on Computer Vision and Machine Learning , particularly 6D object pose estimation , camera localization , and neural-guided optimization . His work bridges classical geometric methods (e.g., RANSAC) with modern deep learning techniques, including differentiable optimization and reinforcement learning for pose estimation. His publications emphasize end-to-end learning , robust model fitting , and RGB-D image analysis , with applications in robotics and 3D scene understanding. Key contributions include DSAC, CONSAC, and neural extensions of RANSAC for efficient hypothesis sampling. 2018 : GI Dissertation Award nomination 2014 : ACCV Honorable Mention Demo Award 2012 : Enno Heidebroek Award for top graduate 2008–2012 : German National Academic Foundation scholarship 2008 : IBM Award for intermediate diploma As a co-organizer of ICCV and ECCV workshops, Eric drives collaboration in visual localization and 6D pose estimation . He has reviewed for CVPR, ICCV, NeurIPS, and TPAMI, earning recognition as an Outstanding Reviewer (CVPR 19, NeurIPS 19). He has held industry roles at IBM (2010–2011) and T-Systems (2008–2009). At TU Dresden and Heidelberg, he taught courses on computer vision and 3D world reconstruction , supervised theses, and developed practical seminars.
Oumeng Zhang serves as a Postdoctoral Scholar Research Associate in Electrical Engineering at the California Institute of Technology, working under Professor Changhuei Yang in the renowned Biophotonics Laboratory. As a Resnick Postdoctoral Scholar, Zhang contributes to cutting-edge research at the intersection of optics, computation, and biomedical applications. Zhang's research interests span multiple advanced imaging domains including biophotonics, computational microscopy, optical imaging, wavefront engineering, Fourier ptychography, non-line-of-sight imaging, and AI applications in medical imaging. The work focuses on developing novel tools that combine optics and microfluidics to tackle diagnostic and measurement problems in biology and medicine, with particular emphasis on pushing the performance of standard microscopes beyond their physical limitations through computational approaches. Analysis of Zhang's recent publications reveals a strong trend toward increasingly sophisticated computational imaging techniques that integrate artificial intelligence with advanced optical methods. The research demonstrates a progression from fundamental optical principles to complex multi-dimensional imaging systems capable of capturing molecular orientation, volumetric structures, and dynamic biological processes with unprecedented resolution. Key thematic areas include polarization imaging, quantitative phase retrieval, neural network-enhanced reconstruction, and multi-view optical systems that achieve isotropic resolution. Resnick Postdoctoral Scholar fellowship Zhang's research is supported through the Resnick Sustainability Institute fellowship and contributes to the broader research portfolio of the Biophotonics Laboratory, which receives funding from multiple federal agencies and private foundations supporting innovative biomedical imaging technologies. The laboratory environment fosters interdisciplinary collaboration between electrical engineers, biologists, and computer scientists working toward transformative diagnostic tools. The research takes place within Caltech's Biophotonics Laboratory, which specializes in developing novel optical tools that combine optics and microfluidics to tackle diagnostic challenges in biology and medicine. Major projects include Fourier Ptychographic microscopy, time-reversal optical focusing, and parallel microscopy systems that transform physical optical problems into computational challenges.
Ioannis Fudos is Professor and former Chair (2014-2018) of the Computer Science and Engineering Department at the University of Ioannina. He holds a Diploma in Computer Engineering from University of Patras, and MS/PhD degrees in Computer Science from Purdue University. His research spans computer graphics, CAD systems, geometric modeling, animation, and image retrieval. He directs the Computer Graphics Research Group and has secured substantial funding (€2M+) from European and national sources for 17+ projects. His scholarly contributions include publications in top venues (SIGGRAPH, Eurographics, IEEE TVCG) covering rendering techniques, 3D printing quality control, assistive technologies, and cultural heritage digitization. Recent work explores neural rendering transparency methods, wheelchair navigation interfaces, and pedestrian routing algorithms. His laboratory maintains a repository of 3D models for research use.
Ling-Qi Yan is an Associate Professor in the Department of Computer Science at the University of California, Santa Barbara (UCSB), where he co-directs the MIRAGE Lab and is affiliated with the Four Eyes Lab. His research focuses on computer graphics, particularly real-time rendering, physically-based appearance modeling, and advanced light transport algorithms. Prior to UCSB, he earned his PhD from UC Berkeley, advised by Ravi Ramamoorthi, and completed internships at Disney, Autodesk, Weta Digital, and NVIDIA Research. He also holds a B.E. in Computer Science from Tsinghua University. Yan's education includes a PhD in Computer Science from UC Berkeley (2018) and a B.E. from Tsinghua University (2013). His research interests span rendering photo-realistic visuals, real-time ray tracing, and appearance modeling for materials like fabrics and fur. Notable achievements include the 2023 EGSR Best Paper Award for cloth shading work and the 2019 ACM SIGGRAPH Outstanding Doctoral Dissertation Award. His awards include the Regents' Junior Faculty Fellowship (UCSB), Best Visual Effects Award (EGSR 2023), and NVIDIA Graduate Fellowship supervision recognition. He teaches courses such as Introduction to Computer Graphics and Real-Time High-Quality Rendering , and has developed online courses in Chinese like GAMES101 and GAMES202 . Yan's lab collaborations and industry ties include roles as a research consultant at Intel and visiting professor at NVIDIA. His research emphasizes bridging theory and practice, with over 50 publications in top venues like SIGGRAPH and ACM Transactions on Graphics.
David Fuentes Jiménez is a Researcher at the Department of Electronics, Universidad de Alcalá, Spain. He is affiliated with the GEINTRA research group focusing on Electronic Engineering applied to Intelligent Spaces and Transport. His doctoral thesis (2021) explored deformable object reconstruction using deep learning techniques, supervised by Dr. Daniel Pizarro Pérez. His research spans computer vision, biomedical signal processing, and smart environments. Key research interests include neural radiance fields in surgery, photoplethysmographic signal dynamics for physiological assessment, and real-time action recognition using depth data. He has contributed to EU projects like GEMS through sensory module development (Ruby). His work integrates deep learning with 3D reconstruction, wearable sensors, and overhead camera systems. Publications highlight innovation in medical imaging, stress detection via PPG signals, and robust people detection algorithms. His work frequently appears in top venues, showcasing interdisciplinary approaches between computer science, biomedical engineering, and robotics. Active in open datasets like GOTPD1, he bridges theory and practical applications in smart spaces and healthcare technology. Education: PhD in Electronics Engineering (2021), Universidad de Alcalá Labs/Teams: GEINTRA Group
João Luiz Dihl Comba is a Professor at the Institute of Informatics, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil. With a PhD in Computer Science from Stanford University (1993-2000) under advisor Leonidas J. Guibas, he has established himself as a leading researcher in visualization and computer graphics. His academic journey includes a M.Sc. in Systems Engineering and Computing from UFRJ (1988-1991) and a B.Sc. in Computer Science from UFRGS (1983-1987), along with a sabbatical at the University of Utah (2010-2011). Comba's research focuses on data and scientific visualization, visual analytics, computer graphics, and their applications in medical imaging, sports analytics, and pandemic response. His work bridges theoretical advances in multidimensional projections with practical applications in healthcare, oil and gas, and digital twins. Recent publications demonstrate his continued leadership in applying machine learning techniques to visualization problems, particularly in biomedical contexts. His publication record spans over three decades with consistent output through 2025, showing evolution from foundational computer graphics work to contemporary applications of AI in visualization. The publications reveal strong collaborations with researchers across Brazil and internationally, with particular emphasis on solving real-world problems through visual analytics. As an advisor, Comba has mentored numerous graduate students who have become active researchers in visualization and computer graphics, with several continuing to collaborate with him on publications. His research group at UFRGS appears to be particularly strong in medical visualization applications, as evidenced by multiple recent publications related to COVID-19 analysis and medical image processing.
Professor Manolya Kavakli-Thorne is a distinguished academic at Aston University, holding dual appointments as Professor of Gamification and Simulation Technology in the College of Engineering and Physical Sciences and the Digital Futures Institute. Her interdisciplinary research spans Human-Computer Interaction (HCI), Virtual/Augmented Reality, and Mixed Reality Systems. Currently supervises 3 PhD students and advises 2 others at Aston University, with prior mentorship of 119 postgraduate students. Total research grants exceed £18.1 million, including major projects like the EU-funded Nexus (€392K) and UKRI Diatomic Accelerator (£8M). Her research focuses on applying gamification to emergency management, cybersecurity, and healthcare. Notable achievements include establishing the first Virtual Reality Lab in Sydney (2005) and the Virtual Production Studio in Canberra (2022). Awards include the 2022 Best Paper Award (IEEE) and multiple top-tier conference recognitions. She has authored over 240 refereed papers and pioneered facilities like CEPET (2015) and SIGMA research groups. Professional roles include Guest Editor for Algorithms (2024) and editorial board memberships across 15+ journals. Her work bridges academia and industry through collaborations with institutions like Birmingham City Council and the ACT Government.
Larry Davis is a Professor in the Department of Computer Science and the Institute for Advanced Computer Studies (UMIACS) at the University of Maryland. He is affiliated with the Computer Vision Laboratory of the Center for Automation Research, where he previously served as head from 1981-1986. His research focuses on visual surveillance, human movement analysis, and advanced computer vision systems such as the Keck Laboratory for the Analysis of Visual Movement. Established in 1998, the Keck Lab uses a 64-camera array to study 3D human motion tracking and shape recognition. His work spans projects like codebook-based background subtraction for surveillance and clothing appearance models for persistent tracking. He leads interdisciplinary research on laser beam propagation through atmospheric turbulence and has secured significant grants, including a $4M Multidisciplinary Research Initiative contract. His recent publications emphasize AI-driven solutions for media forensics, generative models, and adversarial attacks on vision systems. Research contributions include innovations in neural rendering (FlexNeRF), personalized clothing compatibility frameworks, and systems for detecting deepfakes and video tampering. His work bridges theoretical advancements with real-world applications in security, healthcare, and retail technology.
