EE Seminar: Recent Results in 3D scanning
~~(The talk will be given in English)
Speaker: Prof. Andrei Sharf
Computer Science Department, Ben Gurion University
Monday, March 14th, 2016
15:00 - 16:00
Room 011, Kitot Bldg., Faculty of Engineering
Recent Results in 3D scanning
Abstract
The evolution of 3D scanners has made it possible to acquire a large variety of objects such as urban scenes, underwater and lately even motion. The initial representation of the scene consists of several properly transformed depth images, resulting in a point sampling of the object's surface.
Typically, 3D scan data consist of missing parts, noise and outliers.One of today's principal challenges is the development of robust point processing and reconstruction techniques that deal with the inherent inconsistencies in the acquired data set.
In my talk I will present recent advances in processing 3D points data. Motivated by recent advancements in sparse signal reconstruction, I will present a "lower-than-L2" minimization scheme for sparse reconstruction. The sparsity principle gives rise to a novel global reconstruction paradigm for sharp point set surfaces which is robust to noise. Next, I will present a supervised learning algorithm for understanding cluttered indoor scenes. We argue that object classification cannot be directly applied to the scanned scene, since object segmentation is unavailable. Moreover, the segmentation problem is as challenging as classification since spatial relationships between points and patches are neither complete nor reliable. Our key idea is to interleave the segmentation and classification computations, defining a novel search-classify scene understanding framework.
Short bio
ANDREI SHARF is an associate professor at the computer science department at Ben-Gurion University. Previously, he has been a Visiting Associate Professor at the Shenzhen Institute of Advanced Technology(SIAT) Chinese Academy of Sciences and a Postdoctoral researcher at the School of Computer Science in UC-Davis U.S. His research interests are in computer graphics, including geometry processing, interactive techniques, urban modeling and motion reconstruction. In 2012, Sharf received the Eurographics young researcher award for his contributions to the field of 3D point clouds and in a range of related problems.
