Skip to Main content Skip to Navigation
Conference papers

Surface Reconstruction from 3D Line Segments

Pierre-Alain Langlois 1 Alexandre Boulch 2 Renaud Marlet 3, 1
1 imagine [Marne-la-Vallée]
ligm - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
Abstract : In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.
Complete list of metadatas
Contributor : Pierre-Alain Langlois <>
Submitted on : Monday, November 4, 2019 - 9:58:31 AM
Last modification on : Wednesday, February 26, 2020 - 7:06:18 PM

Links full text



Pierre-Alain Langlois, Alexandre Boulch, Renaud Marlet. Surface Reconstruction from 3D Line Segments. 2019 International Conference on 3D Vision (3DV), Sep 2019, Québec City, Canada. pp.553-563, ⟨10.1109/3DV.2019.00067⟩. ⟨hal-02344362⟩



Record views