Multiresolution Banded Refinement to Accelerate Surface Reconstruction from Polygons (1998)
| Venue: | in: Proceedings of the 14th Annual ACM Symposium on Computational Geometry |
| Citations: | 1 - 0 self |
BibTeX
@INPROCEEDINGS{Fix98multiresolutionbanded,
author = {James D. Fix and Richard E. Ladner},
title = {Multiresolution Banded Refinement to Accelerate Surface Reconstruction from Polygons},
booktitle = {in: Proceedings of the 14th Annual ACM Symposium on Computational Geometry},
year = {1998},
pages = {240--248}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We propose a method for constructing a tiling between a pair of planar polygons. Our technique uses multiresolution: tilings of lower resolution polygons are used to construct a tiling for the full resolution polygons. The tilings are constructed using banded refinement, by restricted dynamic programming, in roughly linear time and space. By contrast, the optimal dynamic programming method requires quadratic time and space. In our empirical study of surface reconstruction of brain contours our algorithm exhibited significant speedup over the optimal dynamic program, yet nearly always found an optimal reconstruction. Our approach appears to be generalizable to other geometric problems solvable by dynamic programming, and flexible enough to be tuned for varying data set characteristics. 1 Introduction A typical subproblem of many surface reconstruction algorithms is the fitting of a surface to a set of parallel contours. This problem arises, for example, in medical visualization applic...
