Depth-layer Architecture Reconstruction From Image Collections
Loading...
Date
2014
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
An image-based modeling method is presented to generate a textured 3D model of architecture with a structure
of multiple floors and depth layers. In the domain of image-based architecture modeling, it is still a challenging
problem to deal with architecture in multilayered structure. We propose a statistic-based top-bottom segmentation
algorithm to divide the 3D point cloud generated by structure-from-motion (SFM) method into different floors.
For each floor with depth layers, we present a repetition based depth-layer decomposition algorithm to separate
the front and back layers. Finally, architecture components are modeled to construct a textured 3D model. Our
system has the distinct advantage of producing realistic architecture models with true depth values between front
and back layers, which is demonstrated by multiple examples in the paper.
Description
@inproceedings{:10.2312/sgp20141382,
booktitle = {Symposium on Geometry Processing 2014 - Posters},
editor = {Thomas Funkhouser and Shi-Min Hu},
title = {{Depth-layer Architecture Reconstruction From Image Collections}},
author = {Yong Hu and Bei Chu and Yue Qi},
year = {2014},
publisher = {The Eurographics Association},
ISSN = {-},
ISBN = {-},
DOI = {/10.2312/sgp20141382}
}