Year: 2026
Type: preprint
Abstract: Surface extraction from implicit neural representations modelling a single class surface is a well-known task. However, there exist no surface extraction methods from an implicit representation of multiple classes that guarantee topological correctness and no holes. In this work, we lay the groundwork by introducing a 2D boundary extraction algorithm for the multi-class case focusing on topological consistency and water-tightness, which also allows for setting minimum detail restraint on the approximation. Finally, we evaluate our algorithm using geological modelling data, showcasing its adaptiveness and ability to honour complex topology.
Source: arXiv (Cornell University)
Authors: Vira, Jash, Myers, Andrew, Ratcliffe, Simon
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7130566612
Cites:
Cited by:
Related to: