%0 Conference Proceedings %T Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data %+ imagine [Marne-la-Vallée] %+ Laboratoire d'Informatique Gaspard-Monge (LIGM) %A Chauve, Anne-Laure %A Labatut, Patrick %A Pons, Jean-Philippe %Z http://www.normalesup.org/~labatut/papers/cvpr2010-robust-piecewise-planar.pdf %< avec comité de lecture %( Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on %B CVPR 2010, Twenty-Third IEEE Computer Society Conference on Computer Vision and Pattern Recognition %C San Francisco, United States %I IEEE %P 1261-1268 %8 2010-06-13 %D 2010 %R 10.1109/CVPR.2010.5539824 %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Conference papers %X In this paper, we present a novel method, the first to date to our knowledge, which is capable of directly and automatically producing a concise and idealized 3D representation from unstructured point data of complex cluttered real-world scenes, with a high level of noise and a significant proportion of outliers, such as those obtained from passive stereo. Our algorithm can digest millions of input points into an optimized lightweight watertight polygonal mesh free of self-intersection, that preserves the structural components of the scene at a user-defined scale, and completes missing scene parts in a plausible manner. To achieve this, our algorithm incorporates priors on urban and architectural scenes, notably the prevalence of vertical structures and orthogonal intersections. A major contribution of our work is an adaptive decomposition of 3D space induced by planar primitives, namely a polyhedral cell complex. We experimentally validate our approach on several challenging noisy point clouds of urban and architectural scenes. %G English %L hal-00654408 %U https://enpc.hal.science/hal-00654408 %~ ENPC %~ CSTB %~ CNRS %~ UNIV-MLV %~ LIGM_A3SI %~ PARISTECH %~ LIGM %~ CV_LIGM %~ IMAGINE %~ ESIEE-PARIS %~ UNIV-EIFFEL %~ UPEM-UNIVEIFFEL %~ ESIEE-UNIVEIFFEL %~ TEST3-HALCNRS