Browsing by Subject "Ray casting"

Now showing 1 - 3 of 3

Open Access
Fast direct volume rendering of unstructured grids
(1997-09) Berk, Hakan
Scientific computing has become more and more important with the evolving technology. The vast amount of data that the scientific computing applications produce need new ways to be processed and interpreted by scientists. The large amount of data makes it very difficult for scientists to extract useful information from the data, and interpret it to reach a useful conclusion. Thus. visualization of such numerical data as an image, which is known as Scientific Visualization, is an indispensable tool for researchers. Volume Rendering is a very important branch of Scientific Visualization and makes it possible for scientists to visualize the 3-dimensional (3D) volumetric datasets. Volume Rendering algorithms can be classified into two categories: Indirect and Direct methods. Indirect methods are faster, but direct methods are more flexible and acurate. Direct methods can be classified into three categories: image-space (ray-casting), object-space (projection) and hybrid. The efficiency of a direct volume rendering (DVR) algorithm is strongly related to the way that it solves the underlying point location and view sort problems. Although these problems are almost trivial ones to solve in structured grids, they become more complex ones to deal with for unstructured grids. Researchers have tried to speed up the volume rendering of unstructured grids by using special graphics hardware, and parallel architectures, but the need for software solutions to these problems will always exist. These thesis is involved in solving those problems in unstructured grids via software methods. It investigates three distinct categories, namely image-space methods, object-space methods and hybrid methods for fast direct volume rendering of unstructured grids. The main objective of the thesis is to identify the relative superiorities and inferiorities of the algorithms in these three categories. A survey of existing methods is enriched by a discussion of their merits and shortcomings. Three new and fast algorithms to overcome the existing inefficiencies are proposed, and one existing algorithm is investigated in detail for better comparision. All of the proposed algorithms are aimed at producing correct, high quality images. Two of the proposed algorithms are pure ray-casting based solutions that support early ray termination and can handle cyclic grids. The relative performances of the proposed algorithms are experimented on a wide range of benchmark grids in a common framework for software methods and they are found to be faster than the existing best DVR algorithms.
Open Access
Hypergraph-partitioning-based remapping models for image-space-parallel direct volume rendering of unstructured grids
(Institute of Electrical and Electronics Engineers, 2007-07) Cambazoglu, B. B.; Aykanat, Cevdet
In this work, image-space-parallel direct volume rendering (DVR) of unstructured grids is investigated for distributed-memory architectures. A hypergraph-partitioning-based model is proposed for the adaptive screen partitioning problem in this context. The proposed model aims to balance the rendering loads of processors while trying to minimize the amount of data replication. In the parallel DVR framework we adopted, each data primitive is statically owned by its home processor, which is responsible from replicating its primitives on other processors. Two appropriate remapping models are proposed by enhancing the above model for use within this framework. These two remapping models aim to minimize the total volume of communication in data replication while balancing the rendering loads of processors. Based on the proposed models, a parallel DVR algorithm is developed. The experiments conducted on a PC cluster show that the proposed remapping models achieve better speedup values compared to the remapping models previously suggested for image-space-parallel DVR. © 2007 IEEE.
Open Access
Spatial subdivision for parallel ray casting/tracing
(1995) İşler, Veysi
Ray casting/tracing has been extensively studied for a long time, since it is an elegant way of producing realistic images. However, it is a computationally intensive algorithm. In this study, a taxonomy of parallel ray casting/tracing algorithms is presented cind the primary parallel ray casting/tracing systems are discussed and criticized. This work mainly focuses on the utilization of spatial subdivision technique for ray casting/tracing on a distributed-memory MIMD parallel computer. In this research, the reason for the use of parallel computers is not only the processing power but also the large memory space provided by them. The spatial subdivision technique has been adapted to parallel ray casting/tracing to decompose a three-dimensional complex scene that may not fit into the local memory of a single processor. The decomposition method achieves an even distribution of scene objects while allowing to exploit graphical coherence. Additionally, the decomposition method produces three-dimensional volumes which are mapped inexpensively to the processors so that the objects within adjacent volumes are stored in the local memories of close processors to decrease interprocessor communication cost. Then, the developed decomposition and mapping methods have been parallelized efficiently to reduce the preprocessing overhead. Finally, a splitting plane concept (called “jaggy splitting plane”) has been proposed to accomplish full utilization of the memory space of processors. Jaggy splitting plane avoids the shared objects which are the major sources of inefficient utilization of both memory and processing power. The proposed parallel algorithms have been implemented on the Intel iPSC/2 hypercube multicomputer (distributed-memory MIMD).