Manifold surface reconstruction of an environment from sparse Structure-from-Motion data |
| |
Authors: | Maxime Lhuillier Shuda Yu |
| |
Affiliation: | Institut Pascal (ex. LASMEA), UMR 6602, CNRS/UBP/IFMA, Campus Universitaire des Cézeaux, 63171 Aubière Cedex, France |
| |
Abstract: | The majority of methods for the automatic surface reconstruction of an environment from an image sequence have two steps: Structure-from-Motion and dense stereo. From the computational standpoint, it would be interesting to avoid dense stereo and to generate a surface directly from the sparse cloud of 3D points and their visibility information provided by Structure-from-Motion. The previous attempts to solve this problem are currently very limited: the surface is non-manifold or has zero genus, the experiments are done on small scenes or objects using a few dozens of images. Our solution does not have these limitations. Furthermore, we experiment with hand-held or helmet-held catadioptric cameras moving in a city and generate 3D models such that the camera trajectory can be longer than one kilometer. |
| |
Keywords: | 2-Manifold reconstruction 3D Delaunay triangulation Steiner vertices Complexity analysis Sparse point cloud Structure-from-Motion |
本文献已被 ScienceDirect 等数据库收录! |