Share Email Print
cover

Proceedings Paper

Advanced texture filtering: a versatile framework for reconstructing multi-dimensional image data on heterogeneous architectures
Author(s): Stefan Zellmann; Yvonne Percan; Ulrich Lang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Reconstruction of 2-d image primitives or of 3-d volumetric primitives is one of the most common operations performed by the rendering components of modern visualization systems. Because this operation is often aided by GPUs, reconstruction is typically restricted to first-order interpolation. With the advent of in situ visualization, the assumption that rendering algorithms are in general executed on GPUs is however no longer adequate. We thus propose a framework that provides versatile texture filtering capabilities: up to third-order reconstruction using various types of cubic filtering and interpolation primitives; cache-optimized algorithms that integrate seamlessly with GPGPU rendering or with software rendering that was optimized for cache-friendly "Structure of Array" (SoA) access patterns; a memory management layer (MML) that gracefully hides the complexities of extra data copies necessary for memory access optimizations such as swizzling, for rendering on GPGPUs, or for reconstruction schemes that rely on pre-filtered data arrays. We prove the effectiveness of our software architecture by integrating it into and validating it using the open source direct volume rendering (DVR) software DeskVOX.

Paper Details

Date Published: 8 February 2015
PDF: 11 pages
Proc. SPIE 9397, Visualization and Data Analysis 2015, 93970C (8 February 2015); doi: 10.1117/12.2077927
Show Author Affiliations
Stefan Zellmann, Univ. zu Köln (Germany)
Yvonne Percan, Univ. zu Köln (Germany)
Ulrich Lang, Univ. zu Köln (Germany)


Published in SPIE Proceedings Vol. 9397:
Visualization and Data Analysis 2015
David L. Kao; Ming C. Hao; Mark A. Livingston; Thomas Wischgoll, Editor(s)

© SPIE. Terms of Use
Back to Top