Computer Science and Engineering
Ramamoorthi’s research group develops the theoretical foundations, mathematical representations and computational models for the visual appearance of objects, digitally recreating or rendering the complexity of natural appearance. Ramamoorthi’s research has had significant impact in industry. His work on spherical harmonic lighting and irradiance environment maps is now widely included in games (such as the Halo series), and is increasingly adopted in movie production.
One of Jensen’s major contributions is the photon mapping algorithm for simulating global illumination in complex, three-dimensional scenes such as those used in architecture, design and visual effects for film. Jensen also developed the first methods capable of rendering translucent materials such as snow, marble, milk and human skin. He received an Academy Award for technical achievement in 2004.
Kriegman is one of the most widely cited experts on the subject of face recognition, whose application includes social networking, robotics, human computer interaction, as well as homeland security purposes. Kriegman’s research in computer vision uses machine learning, geometry and physics, and he applies it to diverse areas of computer graphics, medical images, electron microscopy, and coral ecology.
Li’s research focuses on the interactions between three domains: visual computing, programming systems, and statistical learning. He connects classical computer graphics and image processing algorithms with modern data-driven methods to facilitate physical understanding. His work added 3D understanding to computer vision models; used data to improve camera imaging pipeline quality; and made light transport simulation faster by using information implicitly defined by rendering programs.
Chandraker’s research focuses on 3D reconstruction and scene understanding. He has developed theoretical frameworks and practical systems for applications in autonomous driving, robotics, 3D modeling and human-computer interfaces. He has led collaborations with the automobile industry aiming towards low-cost, real-time visual systems for navigation, 3D localization and recognition in traffic scenes.
Su's research lies in broad disciplines related to artificial intelligence, including machine learning, computer vision, computer graphics, and robotics, with a focus on deep learning for 3D data understanding and interconnecting 3D data with other modalities such as images and texts. He is leading the construction of ShapeNet, a large-scale 3D-centric knowledge base of objects, and worked on ImageNet, a large-scale dataset of 2D images. Potential applications for Su's research include robotics, autonomous driving, virtual/augmented reality, smart manufacturing, etc.
With backgrounds in both numerical analysis and differential geometry, Chern studies the interplay among differential geometry, algebraic topology, differential equations, and computational mathematics. This includes physical modeling in geometric language, and discretization methods that preserves structures in their continuous analogs. The research direction has given successful and novel applications in fluid dynamics, geometry processing, as well as classical numerical PDE challenges such as absorbing boundary conditions in wave computations.
Electrical and Computer Engineering
Vasconcelos heads the Statistical Visual Computing Laboratory (SVCL) at UC San Diego. SVCL performs research in both fundamental and applied problems in computer vision, image processing, machine learning, and multimedia. The focus is on the development of intelligent systems, which combine image-understanding capabilities with any available additional information (in the form of supervision, annotations, user feedback, etc.) to enable sophisticated recognition, parsing, retrieval, classification, indexing, browsing, modeling, and compression of visual content. Strong emphasis is given to (1) statistical formulations that can deal with noise and uncertainty and (2) the search for solutions that are provably optimal under suitable optimality criteria.
Wang’s research lies in exploiting the structure in data for learning visual representations, with a focus on the spatial-temporal structure in videos and its connection to 3D structure as well as semantic structure. There are two principal directions he has explored: first, to use the structure information from the data itself as a supervisory signal for learning visual representations (i.e., self-supervised learning), eliminating the need for manual labels; second, to explicitly model the structure in data for human activity analysis, scene affordance reasoning and learning object interaction, with potential applications in robotics. Wang will join UC San Diego in 2020.
Qualcomm Institute At UC San Diego
Since coming to UC San Diego in 2005, DeFanti's team has developed the StarCAVE, NexCAVE, TourCAVE, WAVE, and 4KAVE virtual reality (VR) systems and large-scale 10/40/100Gbs networks connections for visualization. DeFanti and Dan Sandin conceived the CAVE virtual reality theater in 1991. DeFanti is a research scientist at UC San Diego's Qualcomm Institute and a distinguished professor emeritus of Computer Science at the University of Illinois at Chicago. He received the 1988 ACM Outstanding Contribution Award and became an ACM Fellow in 1994.
Schulze’s research focuses on making interactive 3D visualization systems easier to use. This includes both the visual display of the data and input paradigms. He uses high-end clustered graphics systems, such as virtual reality CAVEs to immerse the user in the data and 3D tracked input devices and more recently smart phones and tablets to interact with the virtual reality system.
Tu’s research is at the intersection of computer vision, machine learning, neural computation and cognition and neuroimaging. His research group has been specifically focused on studying statistical learning/computing models for structured, large-scale, and multi-modality data prediction. His research has broad applications, notably for medical imaging.