Learning Delaunay Surface Elements for Mesh Reconstruction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Learning Delaunay Surface Elements for Mesh Reconstruction

Résumé

We present a method for reconstructing triangle meshes from point clouds. Existing learning-based methods for mesh reconstruction mostly generate triangles individually, making it hard to create manifold meshes. We leverage the properties of 2D Delaunay triangulations to construct a mesh from manifold surface elements. Our method first estimates local geodesic neighborhoods around each point. We then perform a 2D projection of these neighborhoods using a learned logarithmic map. A Delaunay triangulation in this 2D domain is guaranteed to produce a manifold patch, which we call a Delaunay surface element. We synchronize the local 2D projections of neighboring elements to maximize the manifoldness of the reconstructed mesh. Our results show that we achieve better overall manifoldness of our reconstructed meshes than current methods to reconstruct meshes with arbitrary topology. Our code, data and pretrained models can be found online: https://github.com/mrakotosaon/dse-meshing
Fichier principal
Vignette du fichier
CVPR21_Learning_Delaunay.pdf (10.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04479810 , version 1 (27-02-2024)

Identifiants

Citer

Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov. Learning Delaunay Surface Elements for Mesh Reconstruction. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021, Nashville, France. ⟨10.1109/CVPR46437.2021.00009⟩. ⟨hal-04479810⟩
23 Consultations
3 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More