Robust and Efficient Surface Reconstruction From Range Data

By Patrick Labatut, Jean-Philippe Pons, Renaud Keriven. 2009

192 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Graphics and Computer-Aided Design

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

Large-Scale Data for Multiple-View Stereopsis (2016, methodology): “…in MVS has, to a great degree, converged to an approach where a 3D point cloud model of a scene is ﬁrst reconstructed and then it is transformed into a trian-123 gulated surface (Kazhdan et al. 2006; Mücke et al. 2011; Fuhrmann and Goesele 2014; Goesele et al. 2006; Labatut et al. 2009).”
Signing the Unsigned: Robust Surface Reconstruction from Raw Pointsets (2010, unknown): “This issue can, however, be remedied for data coming from (stereo)photogrammetry where reliable lines of sight are available, as it makes outliers easier to classify as such [LPK09].”
High Accuracy and Visibility-Consistent Dense Multiview Stereo (2012, unknown): “Since the output surface is only used as an initialization for a variational photometric refinement, the photo-consistency term is advantageously replaced with the simple surface quality term E qual of [40] for surface reconstruction from range scans: P (cid:2) .”
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (2020, background): “Visibility or free space methods estimate which subset of 3D space is occupied, often by subdividing space into distinct tetrahedra [32,27,4].”
Reconstructing building mass models from UAV images (2016, methodology): “Compared with previous graph-cut based approaches for surface reconstruction [33,13,14,11], where their formulations are based on either the irregular graph of the Delaunay tetrahedron, or points, or triangulated meshes, our formulation makes use of a graph with a four-neighbor grid structure in 2D ”
Multi-view reconstruction preserving weakly-supported surfaces (2011, methodology): “We build on work [15] which we call base-line method.”
A Survey of Surface Reconstruction from Point Clouds (2017, methodology): “The method of [LPK09] seeks an interior and exterior labeling of tetrahedra from a Delaunay triangulation of the point cloud, formulated as a graph cut problem using line of sight information.”
Range sensor and silhouette fusion for high-quality 3D Scanning (2015, background): “In particular, multiview stereo approaches currently obtain state-of-the-art results in reconstruction purely from multiple calibrated RGB images [12], [6], [13], [16], [21].”
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video (2021, methodology): “In an offline MVS pipeline [37], Poisson reconstruction [19] and Delaunay triagulation [22] are often used to fulfill this purpose.”
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (2022, background): “Explicit representation includes voxels [5, 29] and triangular mesh [3, 4, 14], which are limited by the resolution.”