The Robotics Institute

RI | Seminar | April 8

Robotics Institute Seminar, April 8
Time and Place | Seminar Abstract | Speaker Biography | Speaker Appointments


Signal-Theoretic Representations of Visual Appearance

Ravi Ramamoorthi

Assistant Professor

Columbia University

 

 

 

Time and Place

Mauldin Auditorium (NSH 1305)
Refreshments 3:15 pm
Talk 3:30 pm

Abstract

 

Many problems in computer graphics require compact and accurate representations of the appearance of objects, and the mathematical algorithms to manipulate them.  For instance, high quality real-time rendering needs models for appearance effects like natural illumination from wide-area light sources such as skylight, realistic material properties like velvet, satin, paints, or wood, and shading effects like soft shadows.  These effects are also important in many computer vision problems like recognition and surface reconstruction.

In these problems, we must often deal with complex high-dimensional spaces.  For instance, for real-time relighting in computer graphics, or for lighting-insensitive recognition in computer vision, we must consider the space of images of an object under all possible lighting conditions.  Since the illumination can in principle come from anywhere, the appearance manifold would seem to be infinite-dimensional.  However, one can find lower-dimensional and more compact structures that lead to efficient algorithms.

 

In this talk, we discuss a signal-theoretic approach to representing appearance, where the illumination and reflection function are signals and filters, and we apply many signal-processing tools such as convolution, wavelet-based representation and sparse data interpolation.  These representations and tools are applicable to a variety of problems in computer graphics and vision.  We will present methods for interactive rendering with complex lighting, reflectance and soft shadows, new techniques for acquiring spatially varying reflectance from a sparse set of photographs in image-based rendering, and applications to inverse problems in graphics and vision.

 

 

Speaker Biography

 

Ravi Ramamoorthi is currently an assistant professor of Computer Science at Columbia University, since August 2002, when he received his PhD in computer science from Stanford University.  He is interested in many aspects of computer graphics and vision, including mathematical foundations, real-time photorealistic rendering, image-based and inverse rendering, and lighting and appearance in computer vision.  Earlier this year, he was awarded a Sloan Research Fellowship and an NSF Career award on the "Mathematical and Computational Fundamentals of Visual Appearance for Computer Graphics".

 

 

Speaker Appointments

For appointments, please contact Janice Brochetti (janiceb+@cs.cmu.edu ).


The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.