Scalable Surface Reconstruction with Delaunay-Graph Neural Networks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Computer Graphics Forum Année : 2021

Scalable Surface Reconstruction with Delaunay-Graph Neural Networks

Résumé

We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real-life Multi-View Stereo (MVS) acquisitions. Our method relies on a 3D Delaunay tetrahedralization whose cells are classified as inside or outside the surface by a graph neural network and an energy model solvable with a graph cut. Our model, making use of both local geometric attributes and line-of-sight visibility information, is able to learn a visibility model from a small amount of synthetic training data and generalizes to real-life acquisitions. Combining the efficiency of deep learning methods and the scalability of energy based models, our approach outperforms both learning and non learning-based reconstruction algorithms on two publicly available reconstruction benchmarks.
Fichier principal
Vignette du fichier
2107.06130.pdf (36.7 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03312448 , version 1 (03-08-2021)

Identifiants

Citer

Raphael Sulzer, Loic Landrieu, Renaud Marlet, Bruno Vallet. Scalable Surface Reconstruction with Delaunay-Graph Neural Networks. Computer Graphics Forum, 2021, Eurographics Symposium on Geometry Processing 2021, July 12 – 14, 2021, 40 (5), pp.157 - 167. ⟨10.1111/cgf.14364⟩. ⟨hal-03312448⟩
176 Consultations
16 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More