Patchwork Stereo: Scalable, Structure-Aware 3D Reconstruction in Man-Made Environments - École des Ponts ParisTech Access content directly
Conference Papers Year : 2017

Patchwork Stereo: Scalable, Structure-Aware 3D Reconstruction in Man-Made Environments

Abstract

Abstract: In this paper, we address the problem of Multi-View Stereo (MVS) reconstruction of highly regular man-made scenes from calibrated, wide-baseline views and a sparse Structure-from-Motion (SfM) point cloud. We introduce a novel patch-based formulation via energy minimization which combines top-down segmentation hypotheses using appearance and vanishing line detections, as well as an arrangement of creased planar structures which are extracted automatically through a robust analysis of available SfM points and image features. The method produces a compact piecewise-planar depth map and a mesh which are aligned with the scene's structure. Experiments show that our approach not only reaches similar levels of accuracy w.r.t state-of-the-art pixel-based methods while using much fewer images, but also produces a much more compact, structure-aware mesh in a considerably shorter runtime by several of orders of magnitude.
Fichier principal
Vignette du fichier
WACV-2017-Bourki-et-al.pdf (2.17 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01743262 , version 1 (26-03-2018)

Identifiers

Cite

Amine Bourki, Martin de La Gorce, Renaud Marlet, Nikos Komodakis. Patchwork Stereo: Scalable, Structure-Aware 3D Reconstruction in Man-Made Environments. 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Mar 2017, Santa Rosa, United States. ⟨10.1109/WACV.2017.39⟩. ⟨hal-01743262⟩
65 View
231 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More