提出多类别隐式表示边界提取方法，确保拓扑正确无孔洞。
Multi-Class Boundary Extraction from Implicit Representations
- 基于隐式表示设计2D多类别边界提取算法
- 保证拓扑一致性与表面闭合性，可设定最小细节约束
- 适用于地质建模等复杂拓扑场景
单类别表面的隐式神经表示表面提取已较为成熟，但针对多类别隐式表示的表面提取方法尚缺乏能保证拓扑正确性与无孔洞的方案。本文提出一种聚焦于拓扑一致性和水密性的二维多类别边界提取算法，同时支持对近似结果的最小细节约束。最终在地质建模数据上进行评估，验证了该算法在复杂拓扑下的适应性与保真能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。