Andrei Sharf (Ben-Gurion University)
Thursday, 28.6.2012, 11:30
Today's scanning technologies, allow fast 3D scanning of urban scenes.
Such rapid acquisition incurs imperfections: large regions remain
missing, significant variation in sampling density is common, and the
data is often corrupted with noise and outliers.
Buildings often exhibit large scale repetitions and self-similarities.
To consolidate the imperfect data, our key observation is that the
same geometry, when scanned multiple times over reoccurrences of
instances, allow application of a simple and effective non-local
We also introduce tools for quickly assemble, retarget and abstract
of architectural model. Through manipulation of simple building
blocks, we are able to reconstruct a complex scene and synthesize
it into new appearances.