Towards high-resolution large-scale multi-view stereo

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...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Vu Hoang Hiep, Renaud Keriven, Patrick Labatut, Jean-Philippe Pons
• Keywords: Computer Vision, CVPR 2009, Dense Multi-view Benchmark, Dense Multi-view Stereovision, Multi-view Stereo Pipeline