Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data. Chauve, A., Labatut, P., & Pons, J. In 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1261–1268, June. doi abstract bibtex 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.
@inproceedings{chauve_robust_nodate,
title = {Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data},
doi = {10.1109/CVPR.2010.5539824},
abstract = {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.},
booktitle = {2010 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR})},
author = {Chauve, A.-L. and Labatut, P. and Pons, J.-P.},
month = jun,
pages = {1261--1268}
}
Downloads: 0
{"_id":"dvXqavtYufzm4Logb","bibbaseid":"chauve-labatut-pons-robustpiecewiseplanar3dreconstructionandcompletionfromlargescaleunstructuredpointdata","authorIDs":[],"author_short":["Chauve, A.","Labatut, P.","Pons, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data","doi":"10.1109/CVPR.2010.5539824","abstract":"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.","booktitle":"2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":[{"propositions":[],"lastnames":["Chauve"],"firstnames":["A.-L."],"suffixes":[]},{"propositions":[],"lastnames":["Labatut"],"firstnames":["P."],"suffixes":[]},{"propositions":[],"lastnames":["Pons"],"firstnames":["J.-P."],"suffixes":[]}],"month":"June","pages":"1261–1268","bibtex":"@inproceedings{chauve_robust_nodate,\n\ttitle = {Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data},\n\tdoi = {10.1109/CVPR.2010.5539824},\n\tabstract = {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.},\n\tbooktitle = {2010 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR})},\n\tauthor = {Chauve, A.-L. and Labatut, P. and Pons, J.-P.},\n\tmonth = jun,\n\tpages = {1261--1268}\n}\n\n","author_short":["Chauve, A.","Labatut, P.","Pons, J."],"key":"chauve_robust_nodate","id":"chauve_robust_nodate","bibbaseid":"chauve-labatut-pons-robustpiecewiseplanar3dreconstructionandcompletionfromlargescaleunstructuredpointdata","role":"author","urls":{},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/jtheikkila","creationDate":"2019-09-15T15:10:41.144Z","downloads":0,"keywords":[],"search_terms":["robust","piecewise","planar","reconstruction","completion","large","scale","unstructured","point","data","chauve","labatut","pons"],"title":"Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data","year":null,"dataSources":["rsZGjfhq5jNHuLCRm"]}