Multi-Class Boundary Extraction from Implicit Representations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908839462305792 |
|---|---|
| author | Vira, Jash Myers, Andrew Ratcliffe, Simon |
| author_facet | Vira, Jash Myers, Andrew Ratcliffe, Simon |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Class Boundary Extraction from Implicit Representations Vira, Jash Myers, Andrew Ratcliffe, Simon Machine Learning 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. |
| title | Multi-Class Boundary Extraction from Implicit Representations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.16217 |