Skip to main content

Research Repository

Advanced Search

Surface Reconstruction with Neural Meshes.

Ivrissimtzis, Ioannis; Jeong, Won-Ki; Lee, Seungyong; Lee, Yunjin Lee; Seidel, Hans-Peter

Authors

Won-Ki Jeong

Seungyong Lee

Yunjin Lee Lee

Hans-Peter Seidel



Contributors

M. Daehlen
Editor

K. Morken
Editor

L. Schumaker
Editor

Abstract

We describe a Learning algorithm for surface reconstruction based on an incrementally expanding Neural Network known as Growing Cell Structure. The Neural Network (Neural Mesh) expands by splitting its most active vertices and removing its least active. It learns topologies by removing triangles to create boundaries and merging boundaries to create handles. High-level ensemble and forgetting operations are used to enhance the algorithm’s performance. We study the algorithm theoretically, analyzing statistically its main components, and experimentally, using an extensive range of input data sets with varying amounts of pre-processing.

Citation

Ivrissimtzis, I., Jeong, W., Lee, S., Lee, Y. L., & Seidel, H. (2005). Surface Reconstruction with Neural Meshes. In M. Daehlen, K. Morken, & L. Schumaker (Eds.),

Conference Name Mathematical Methods for Curves and Surfaces.
Conference Location Tromsoe, Norway
Publication Date 2005-05
Pages 223-242
Public URL https://durham-repository.worktribe.com/output/1697755