Keynotes
Sparse View Synthesis
We seek the ability to take a few images of a scene of interest, and turn it into an immersive visual experience, where one can explore it from different viewpoints, in effect visualizing a 3D representation of an object, scene or photograph, and providing numerous applications in augmented reality, e-commerce and 3D photography. This problem, known as view synthesis or image-based rendering in computer vision and graphics, has a three-decade plus history, and is currently undergoing a renaissance with new representations of 3D geometry enabling unparalleled realism. We discuss some of the history in terms of capturing the light field (the space of light rays for any spatial position and viewing direction), and our own work on a sampling theory for view synthesis based on light fields, leading to the development of volumetric radiance fields as a fundamentally new approach to representing 3D geometry for view synthesis. We will also discuss parallels to Monte Carlo and volumetric rendering and simulation problems in computer graphics. We then ask the question of how far we can push the required number of images, in order to achieve sparse view synthesis with very few images, in the limit only one photograph. In this context, we also discuss our recent results on a number of applications including real-time live portraits, generative AI for 3D scenes, and differentiable light transport for inverse rendering.
Speaker
Ravi Ramamoorthi
Ravi Ramamoorthi is the Ronald L. Graham Professor of Computer Science at UCSD and founding director of the UC San Diego Center for Visual Computing. He earlier held tenured faculty positions at UC Berkeley and Columbia University, in all of which he played a key leadership role in building multi-faculty research groups recognized as leaders in computer vision and graphics. He has authored more than 200 refereed publications, including 100+ ACM SIGGRAPH/TOG papers. He has consulted with Pixar and startups in computational imaging, and currently holds a part-time appointment as a Distinguished Research Scientist at NVIDIA. Prof. Ramamoorthi has received more than twenty major honors including the ACM SIGGRAPH Significant New Researcher Award for his research in computer graphics, and the Presidential Early Career Award for Scientists and Engineers for his work on physics-based computer vision. He is a fellow of IEEE, ACM and the SIGGRAPH Academy, received an inaugural Frontiers of Science Award and again the following year, and has twice been honored with the edX Prize certificate for exceptional contributions in online teaching and learning. He has graduated more than 30 postdoctoral and Ph.D. students, whose theses have been recognized by the ACM Dissertation Award honorable mention, the ACM SIGGRAPH outstanding dissertation award and the UCSD Chancellor's Dissertation Medal.
Bridging the Gap Between Academic Benchmarks and Real-World Deployment in Computer Vision: The Path to Translation.
View full detailsApplications of Computer Vision in Healthcare: The Road to Autonomy
Computer vision has become a transformative force in healthcare, enabling machines to see, sense, reconstruct, interpret, and assist in ways once reserved for human experts. This talk explores the evolution from image reconstruction and analysis to autonomous systems that can understand clinical context, reason about uncertainty, and act responsibly. Drawing on advances in deep learning, multimodal foundation models, and agentic AI, we will discuss how autonomous imaging pipelines, precision diagnostics, and intelligent interventions and therapy are shaping the future of patient care. The journey toward autonomy represents not only a technological frontier but also a profound shift in how we design, validate, and trust AI systems in medicine.
Speaker
Dorin Comaniciu
Dr. Comaniciu serves as Senior Vice President and Chief Expert for Healthcare AI at Siemens Healthineers. His scientific contributions to machine intelligence and computational imaging have translated to a multitude of clinical products focused on improving the quality of care, specifically in the fields of diagnostic imaging, image-guided therapy, and precision medicine.
An elected member of the National Academy of Medicine, National Academy of Engineering, and the Romanian Academy, Comaniciu is a Top Innovator of Siemens and a Fellow of the IEEE, ACM, and MICCAI Society, among other scientific organizations. He has received the IEEE Longuet-Higgins Prize for fundamental contributions to computer vision. Recent recognition includes an honorary doctorate from Friedrich-Alexander University of Erlangen-Nuremberg in Germany.
With over 550 granted patents, 350 peer-reviewed papers, 68,000 citations, and an h-index of 110, he has made significant contributions to science and engineering. His work played an important role in advancing medical imaging to become faster and more automated, while providing efficient and precise solutions for detecting, quantifying, and treating disease.
A graduate of University of Pennsylvania's Wharton School, Comaniciu received a doctorate in electrical and computer engineering from Rutgers University and a doctorate in electronics and telecommunications from Polytechnic University of Bucharest.
He is an advocate for technological innovations that save and enhance lives, addressing critical issues in global health.
[https://www.linkedin.com/in/dorincomaniciu/](https://www.linkedin.com/in/dorincomaniciu/)
A short history of video Understanding - Past, Present, and Future
Understanding human actions and events from video has long been a central challenge in computer vision, driven by the fundamental difficulty of making sense of images over time over time. This keynote covers the history of action recognition and video understanding through the lens of the field’s most persistent obstacles. It begins with early approaches that relied on carefully engineered spatiotemporal features, where the core challenge was how to represent motion, dynamics, and temporal structure in a form suitable for learning. After that we will cover how the rise of CNNs brought the shift from handcrafted features to data-driven representations but also how progress became coupled to the availability, scale, and diversity of video datasets and the practical limits this imposed on training deep models. The talk concludes with the current challenges of the field—aligning video with language—where the problem extends beyond recognition to semantic grounding, multimodal representation learning, and reasoning across visual, temporal, and linguistic abstractions. It shows that while video understanding matured the challenge of making sense of visual data over time persisted. By revisiting the history of these challenges, this keynote aims to clarify how past constraints influence today’s solutions and to provide perspective on the open problems that will define the next generation of video understanding systems.
Speaker
Hilde Kühne
Prof. Dr. Hilde Kuehne is a Professor of Multimodal Learning at the Tübingen AI Center and an affiliated professor at the MIT–IBM Watson AI Lab. Previously, she was a Professor of Computer Vision and Multimodal Learning at the University of Bonn. She received her PhD from the cv:hci lab at the Karlsruhe Institute of Technology (KIT), where she was supervised by Rainer Stiefelhagen, and subsequently held postdoctoral positions at Fraunhofer FKIE and in the Computer Vision Group led by Prof. Jürgen Gall. Her research focuses on video understanding, with a particular emphasis on learning without labels and multimodal video understanding. She has created several highly cited datasets and foundational works for analyzing large collections of untrimmed video data, including HMDB51, which was awarded both the ICCV 2021 Helmholtz Prize and the PAMI Mark Everingham Prize. Prof. Kuehne currently serves as an Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence. She was Program Chair for WACV 2024, General Chair for ICCV 2025, and regularly serves as an Area Chair for major conferences such as CVPR, ICCV, ECCV, and WACV. She is strongly committed to increasing diversity in the field and is an active supporter of the Women in Computer Vision initiative.
No Events Found
Try adjusting your search terms
Successful Page Load