Center for Visual Computing launches
|Rendered images of the components in milk as well as mixed concentrations. From left to right, the glasses contain: Water, water and vitamin B2, water and protein, water and fat, skimmed milk, regular milk, and whole milk.|
San Diego, Calif., April 20, 2015 -- Researchers at the University of California, San Diego have launched the UC San Diego Center for Visual Computing, which brings together experts in computer graphics, computer vision, computational imaging and augmented reality with the goal of making significant, long-term contributions to visual computing and imaging technologies.
“We are researching and developing a future in which we can render photograph-quality images instantly on mobile devices; a future in which computers and wearable devices have the ability to see and understand the physical world just as humans do; a future in which real and virtual content merge seamlessly across different platforms,” said Ravi Ramamoorthi, director of the center and a professor in the Department of Computer Science and Engineering at UC San Diego.
The field of visual computing is undergoing unprecedented growth thanks to the advent of new sensors, new methods for the creation of realistic images at interactive rates and new algorithms for deep learning. Visual computing also is becoming increasingly important for robotics.
“It’s a very exciting moment to develop research that could make a big impact,” said Zhuowen Tu, a professor in the Department of Cognitive Science at UC San Diego and one of the center’s faculty members. “It’s about sensors, data, applications, large-scale computing, representations, and machine learning algorithms. We will bring them together like never before.”
The center researchers and corporate partners will focus on three research themes:
- Mobile Visual Computing and Digital Imaging
Changing the way we image, display and capture the visual world by developing techniques to capture the environment via mobile devices, improved computational imaging, computer vision in the wild, and advanced rendering on mobile platforms.
- Interactive Digital (Augmented) Reality
Achieving real-time photorealism; the creation of photograph-quality images at interactive frame rates to enable digital reality rendered in real time. Developing the ability to render and mix real and virtual content seamlessly and realistically in real-time.
- Understanding People and their Surroundings
Automating computer understanding of our visual world, from the imaging of small-scale underwater organisms, to everyday environments, to the scale of a large city. Applications include core vision technology for computational photography; understanding of city forensics at a large scale; and recognition of urban tribes, such as bikers or surfers.
The center is one of Dean Al Pisano’s Agile Centers, bringing together multidisciplinary faculty who engage industry to be highly relevant to real-world problems. Corporate partners are as interested in the solutions from the center’s work as well as the talent that the center will graduate. The center will give its members access to unique facilities, such as the WAVE, or Wide-Angle Virtual Environment, an array of 35 55” LG commercial LCD monitors that end in a crest at the viewers’ head and a ‘trough’ at their feet. Housed at the Qualcomm Institute on the UC San Diego campus, the 3D-enabled display is unique in the world and was designed to serve as both a microscope and telescope, enabling users to explore date from the nano to mega scale. The WAVE, a project led by UC San Diego researchers Falko Kuester and Tom DeFanti, unlike other virtual and augmented reality environments, allows 20 or more people to view content at the same time. The Qualcomm Institute has long been a leader in the field of augmented and virtual reality, center director Ramamoorthi said.
The center currently has the following industry sponsors: Sony, Adobe, Pixar and Qualcomm.
The center’s five core faculty are:
Director: Professor Ravi Ramamoorthi, Department of 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.
Professor Henrik W. Jensen, Department of Computer Science and Engineering
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.
Professor David Kriegman, Department of Computer Science and Engineering
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.
Research Scientist Jurgen Schulze, Qualcomm Institute
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.
Professor Zhuowen Tu, Department of Cognitive Science
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.
Visit the Center’s website at http://viscomp.ucsd.edu