Towards high-resolution large-scale multi-view stereo

Abstract

Boosted by the Middlebury challenge, the precision of dense multi-view stereovision methods has increased drastically in the past few years. Yet, most methods, although they perform well on this benchmark, are still inapplicable to large-scale data sets taken under uncontrolled conditions. In this paper, we propose a multi-view stereo pipeline able to deal at the same time with very large scenes while still producing highly detailed reconstructions within very reasonable time. The keys to these benefits are twofold: (i) a minimum s-t cut based global optimization that transforms a dense point cloud into a visibility consistent mesh, followed by (ii) a mesh-based variational refinement that captures small details, smartly handling photo-consistency, regularization and adaptive resolution. Our method has been tested on numerous large-scale outdoor scenes. The accuracy of our reconstructions is also measured on the recent dense multi-view benchmark proposed by Strecha et al., showing our results to compare more than favorably with the current state-of-the-art.

Range and Image Data Integration for Man-Made Object Reconstruction

“…Nowadays, LiDAR and photogrammetric point clouds can indeed be considered comparable in most cases in terms of density and accuracy, as asserted in several papers both in terrestrial (Remondino et al, 2008;Hiep et al, 2009) and aerial applications (Paparoditis et al, 2006;Hirshmuller, 2008;Gehrke et al, 2010). In typical mapping and modelling applications, once a point cloud (usually several millions of points) has been extracted, only the first (and shortest) part of the work has been completed.…”

Detailed Primitive-Based 3d Modeling of Architectural Elements

“…, 2011). Indeed the potentialities of the image-based approach with respect to range-based / LiDAR methods is getting more and more evident, thanks to the latest developments in dense image matching (Hirschmueller 2008;Remondino et al 2008;Hiep et al 2009;Furukawa and Ponce 2010;Jachiet et al, 2010;Hirschmueller, 2011) and the availability of web-based and open-source processing tools (e.g. Photosynth, 123DCatch, Apero, MicMac, etc.).…”

Multi-View Stereo: A Tutorial

“…a building facade or a fountain, then scaled up to much larger scenes, e.g. entire buildings and cities [129,153,97,69]. These major changes were not solely due to the developments in the MVS field itself.…”