2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2010
DOI: 10.1109/cvpr.2010.5539824
|View full text |Cite
|
Sign up to set email alerts
|

Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data

Abstract: http://www.normalesup.org/~labatut/papers/cvpr2010-robust-piecewise-planar.pdfInternational audienceIn 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 a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
173
0

Year Published

2012
2012
2019
2019

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 156 publications
(173 citation statements)
references
References 28 publications
0
173
0
Order By: Relevance
“…It can be accomplished via various approaches, such as voxel rasterization (Chehata et al, 2009;Paris et al, 2006), 3D Delaunay triangulation (Labatut et al, 2007;Labatut et al, 2009) and space subdivision by hyperplanes (Chauve et al, 2010;Oesau et al, 2014). Note that the surfaces of the reconstructed building are the subset of the volumetric surfaces derived from space partitioning.…”
Section: Space Partitioningmentioning
confidence: 99%
See 1 more Smart Citation
“…It can be accomplished via various approaches, such as voxel rasterization (Chehata et al, 2009;Paris et al, 2006), 3D Delaunay triangulation (Labatut et al, 2007;Labatut et al, 2009) and space subdivision by hyperplanes (Chauve et al, 2010;Oesau et al, 2014). Note that the surfaces of the reconstructed building are the subset of the volumetric surfaces derived from space partitioning.…”
Section: Space Partitioningmentioning
confidence: 99%
“…Space partitioning is a necessary step for surface reconstruction via graph cuts (Chauve et al, 2010;Oesau et al, 2014). It can be accomplished via various approaches, such as voxel rasterization (Chehata et al, 2009;Paris et al, 2006), 3D Delaunay triangulation (Labatut et al, 2007;Labatut et al, 2009) and space subdivision by hyperplanes (Chauve et al, 2010;Oesau et al, 2014).…”
Section: Space Partitioningmentioning
confidence: 99%
“…The carving method described in this paper results in much higher detail. There exist techniques that attempt to mitigate the above factors for architecture modeling, but they often require computationally expensive global optimizations [6]. Those approaches work well for a limited modeling environment, but do not scale well.…”
Section: Introductionmentioning
confidence: 99%
“…Those approaches work well for a limited modeling environment, but do not scale well. The largest tested model in [6] consists of 3.3 million points, whereas the example models in this paper contain 13 million to 115 million points. The desired technique is one that uses a volumetric approach to ensure watertightness and preserves sharp, planar features as well as fine detail, but is fast and memory efficient even with large models.…”
Section: Introductionmentioning
confidence: 99%
“…A releted stream of work is those referred to as "planar stereo" [22,23,24], where one aims at obtaining a piecewise planar representation of scene starting from dense multiview stereo. In this work, instead, we face a more di cult problem, for we start with the sparse output of structure-and-motion, thereby avoiding the multiview stereo stage.…”
Section: Introductionmentioning
confidence: 99%