🤖 AI Summary
This work proposes a novel boundary extraction algorithm that addresses the challenge of recovering topologically consistent and watertight (hole-free) two-dimensional boundaries from multi-class implicit representations—a task where existing methods often fail. The method achieves, for the first time, topologically accurate and watertight boundary reconstruction under multi-class implicit settings, while incorporating a minimal detail constraint mechanism to control geometric approximation fidelity. Built upon implicit neural representations, the approach effectively preserves both boundary completeness and topological correctness. Experimental results on geological modeling datasets demonstrate that the algorithm accurately reconstructs complex topological structures, exhibiting strong adaptability and robustness across diverse scenarios.
📝 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.