Robotics Institute
Seminar, April 8
Time
and Place | Seminar Abstract | Speaker
Biography | Speaker Appointments
Signal-Theoretic Representations of Visual
Appearance
|
Assistant Professor |
Time and Place |
Mauldin
Auditorium (NSH 1305)
Refreshments
Talk
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
For appointments, please contact Janice Brochetti (janiceb+@cs.cmu.edu
).
The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.