Project

Back to overview

Stream-Based Processing of Points

English title Stream-Based Processing of Points
Applicant Pajarola Renato
Number 111746
Funding scheme Project funding (Div. I-III)
Research institution Institut für Informatik Universität Zürich
Institution of higher education University of Zurich - ZH
Main discipline Information Technology
Start/End 01.04.2006 - 31.03.2009
Approved amount 243'373.00
Show all

Keywords (5)

Computer Graphics; Scientific Visualization; Large-Scale Data Processing and Visualization; visualization; point processing

Lay Summary (English)

Lead
Lay summary
Points as rendering and modeling primitives have become a powerful basis for 3D object representation. In particular, points are the natural raw output data of the capturing stage in 3D geometry acquisition systems.Capturing of 3D objects and environments has become a central and mission critical activity in content acquisition and creation application domains such as physical asset management, CAD/CAM, GIS, consumer product design, marketing and e-entertainment. With the dramatically increasing precision of 3D capturing systems, a major challenge is to cope with the huge volume of raw point sample data that these systems generate. The focus of this proposal is the definition and implementation of a novel concept for streaming processing and visualization of very large 3D point data sets.In this context, the major challenges in dealing with points encompass:(1) develop efficient point processing algorithms and (2) improve visualization techniques. In particular, efficient data processing in all stages with limited main memory usage and accessing data in a memory-access coherent sequential order has been left out so far.The central contribution of this proposal lies in new sequential methods to process and visualize large-scale point data sets. In particular, the proposed techniques exhibit minimal main memory usage and directly support out-of-core implementation. The central research part of this proposal introduces the novel and extremely powerful stream-processing concept for point processing. Furthermore, we address sequential multiresolution modeling and rendering.- A new fundamental stream-processing concept to implement a wide range of operations and functions on points as operators that can be chained together and applied to a stream of points.- Sequentialization of multiresolution point data representations, and extension of point visualization techniques to sequential out-of-core streaming, caching and rendering.The proposed project will impact both research and application of points in graphics and visualization. In terms of research, the novel capturing and stream-based point processing and rendering concepts will spur new research in sample based graphics, and point-based visualization in particular. A novel research focus on stream-based point processing techniques is initiated that will have a salient influence on other areas of computer graphics, geometric modeling or scientific visualization. In fact, scientific visualization very often deals with discrete sample based and very large scale data sets.
Direct link to Lay Summary Last update: 21.02.2013

Responsible applicant and co-applicants

Employees

Associated projects

Number Title Start Funding scheme
116329 VISS: Visualization Infrastructures for Scalable Scientific Computing 01.04.2007 Project funding (Div. I-III)

-