Work

Scalable Surface Reconstruction with Delaunay‐Graph Neural Networks

Year: 2021

Type: article

Abstract: 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.

Source: Computer Graphics Forum

DOI: 10.1111/cgf.14364

Authors: R. Sulzer, L. Landrieu, R. Marlet, B. Vallet

Institutions: Centre National de la Recherche Scientifique, Institut national de l’information géographique et forestière, Laboratoire d'Informatique Gaspard-Monge, Université Gustave Eiffel, Valeo (France)

Language: English

Topic: 3D Shape Modeling and Analysis

Subfield: Computational Mechanics

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: Building Indoor/Outdoor Modeling