Arts & Sciences Events
This calendar presented by
Arts & Sciences
[PAST EVENT] Computer Science Colloquium: Materials in the Wild
October 10, 2014
3pm
Kavita Bala, Cornell University
Our daily lives bring us in contact with a rich range of materials that contribute to both the utility and aesthetics of our environment. Human beings are remarkably good at making subtle distinctions in material appearance (e.g.,silk vs. cotton, laminate vs. granite). In my group, we are working on understanding how humans perceive materials, to drive better graphics and vision algorithms. I will present OpenSurfaces, a rich, labeled database of thousands of material examples segmented from consumer photographs using crowd sourcing. We demonstrate the use of this database in applications like intrinsic image decomposition, intelligent material-based image browsing, and material design. I will also describe some recent work on modeling materials like fabrics and translucent media for realistic appearance. This work has applications in many domains: in virtual and augmented reality fueled by the advent of devices like Google Glass, in e-commerce and retail, and in virtual prototyping for industrial, interior, and textile design.
Biography:
Kavita Bala is an Associate Professor in the Computer Science Department at Cornell University. She received her Ph.D. from the Massachusetts Institute of Technology (MIT). Bala leads research projects in physically-based scalable rendering, perceptually-based graphics, material perception and acquisition, and image-based modeling and texturing. Her group's scalable rendering research on Lightcuts is the core rendering technology in Autodesk's cloud rendering platform. Bala's professional activities include Chair of SIGGRAPH Asia 2011, co-Chair of Pacific Graphics (2010) and the Eurographics Symposium on Rendering (2005), Papers Advisory Board for SIGGRAPH and SIGGRAPH Asia, Senior Associate Editor for TOG, and Associate Editor for TVCG and CGF. She has received the NSF CAREER award, and Cornell's College of Engineering James and Mary Tien Excellence in Teaching Award (2006 and 2009).
Our daily lives bring us in contact with a rich range of materials that contribute to both the utility and aesthetics of our environment. Human beings are remarkably good at making subtle distinctions in material appearance (e.g.,silk vs. cotton, laminate vs. granite). In my group, we are working on understanding how humans perceive materials, to drive better graphics and vision algorithms. I will present OpenSurfaces, a rich, labeled database of thousands of material examples segmented from consumer photographs using crowd sourcing. We demonstrate the use of this database in applications like intrinsic image decomposition, intelligent material-based image browsing, and material design. I will also describe some recent work on modeling materials like fabrics and translucent media for realistic appearance. This work has applications in many domains: in virtual and augmented reality fueled by the advent of devices like Google Glass, in e-commerce and retail, and in virtual prototyping for industrial, interior, and textile design.
Biography:
Kavita Bala is an Associate Professor in the Computer Science Department at Cornell University. She received her Ph.D. from the Massachusetts Institute of Technology (MIT). Bala leads research projects in physically-based scalable rendering, perceptually-based graphics, material perception and acquisition, and image-based modeling and texturing. Her group's scalable rendering research on Lightcuts is the core rendering technology in Autodesk's cloud rendering platform. Bala's professional activities include Chair of SIGGRAPH Asia 2011, co-Chair of Pacific Graphics (2010) and the Eurographics Symposium on Rendering (2005), Papers Advisory Board for SIGGRAPH and SIGGRAPH Asia, Senior Associate Editor for TOG, and Associate Editor for TVCG and CGF. She has received the NSF CAREER award, and Cornell's College of Engineering James and Mary Tien Excellence in Teaching Award (2006 and 2009).