Scalable Surface Reconstruction with Delaunay‐Graph Neural Networks

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 t...

Full description

Bibliographic Details

Published in:	Computer graphics forum Vol. 40; no. 5; pp. 157 - 167
Main Authors:	Sulzer, R., Landrieu, L., Marlet, R., Vallet, B.
Format:	Journal Article
Language:	English
Published:	Oxford Blackwell Publishing Ltd 01.08.2021 Wiley
Series:	Eurographics Symposium on Geometry Processing 2021, July 12 – 14, 2021
Subjects:	Algorithms CCS Concepts Computer Science Computing methodologies → Reconstruction Deep learning Graph neural networks Machine learning Neural networks Reconstruction Shape inference Visibility
ISSN:	0167-7055, 1467-8659
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!