COURSE: Adaptive Manifolds for Real-Time High-Dimensional Filtering (SIGGRAPH 2012). Prof. Manuel de Oliveira


May 24, 2012 from 11:00 AM to 12:00 PM (Europe/Madrid / UTC200)


Building U, room 002, Campus Sud

Add event to calendar


Prof. Manuel de Oliveira
Universidade Federal do Rio Grande do Sul
Porto Alegre, Brazil

ABSTRACT. Adaptive Manifolds for Real-Time High-Dimensional Filtering
          (SIGGRAPH 2012)

I will present a technique for performing high-dimensional filtering
of images and videos in real time. Our approach produces high-quality
results and accelerates filtering by computing the filter’s response
at a reduced set of sampling points, and using these for interpolation
at all N input pixels. We show that for a proper choice of these
sampling points, the total cost of the filtering operation is linear
both in N and in the dimension d of the space in which the filter
operates. As such, ours is the first high-dimensional filter with such
a complexity. I will present formal derivations for the equations that
define our filter, as well as for an algorithm to compute the sampling
points. This provides a sound theoretical justification for our method
and for its properties. The resulting filter is quite flexible, being
capable of producing responses that approximate either standard
Gaussian, bilateral, or non-local-means filters. Such flexibility also
allows us to demonstrate the first hybrid Euclidean-geodesic filter
that runs in a single pass. Our filter is faster and requires less
memory than previous approaches, being able to process a 10-Megapixel
full-color image at 50 fps on modern GPUs. We illustrate the
effectiveness of our approach by performing a variety of tasks ranging
from edge-aware color filtering in 5-D, noise reduction (using up to
147 dimensions), single-pass hybrid Euclidean-geodesic
filtering, and detail enhancement, among others.

Ha obtenido financiación de la Dirección General de Política Universitaria, Ministerio de Educación, Cultura y Deporte, a través de las subvenciones para profesores visitantes en programas de masteres oficiales.