A Parallel Pipeline Convolution for Perspective Projection in Real-Time Volume Rendering

DSpace/Manakin Repository

A Parallel Pipeline Convolution for Perspective Projection in Real-Time Volume Rendering

Citable link to this page


Title: A Parallel Pipeline Convolution for Perspective Projection in Real-Time Volume Rendering
Author: Ogata, Masato; Ohkami, Takahide; Pfister, Hanspeter; Lauer, Hugh C.; Dohi, Yasunori

Note: Order does not necessarily reflect citation order of authors.

Citation: Ogata, Masato, Takahide Ohkami, Hanspeter Pfister, Hugh C. Lauer, and Yasunori Dohi. 2000. A parallel pipeline convolution for perspective projection in real-time volume rendering. Journal of the Institute of Image Information and Television Engineers 54(9): 1339-1348.
Full Text & Related Files:
Abstract: This paper describes a convolution with a systolic array structure for perspective projection in real-time volume graphics based on the shear-warp method. In the original method, the further the ray proceeds, the more voxels are required to calculate the convolution. The increase in required voxels makes it difficult to implement the method in a VLSI-oriented architecture. We implement a 3D convolution using three serial 1D convolutions along the X, Y, and Z axes, which reduces the number of calculation units from M3 to 3M, where the convolution is calculated for the M3 area. The number of pipelines for the rays is V2 for V3 voxel datasets. If the hardware of a single pipeline can calculate the V rays, then each of the implemented pipelines is assigned to V theoretical pipelines (for V2 rays). The number of hardware pipelines should be much smaller than V theoretical pipelines in actual implementation. We folded the theoretical pipelines and reduced them to a certain number of hardware pipelines. We examined the relation between the folding process and its necessary time delay. The architecture can generate an image of a 2563 voxel dataset (V=256) at 30Hz with four pipelines. In addition, the architecture can be extended easily for 5123 (V=512) and 10243 (V=1024) datasets, with 32 pipelines and 256 pipelines. Our architecture has processing scalability.
Published Version: http://sciencelinks.jp/j-east/article/200102/000020010200A0952145.php
Other Sources: http://gvi.seas.harvard.edu/sites/all/files/Ieicee5.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAA
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:4238983
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)


Search DASH

Advanced Search