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

Amine Bourki (1) , Martin de La Gorce (1) , Renaud Marlet (1) , Nikos Komodakis (1)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge

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.

Domains: Computer Vision and Pattern Recognition [cs.CV]

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⟩