Title :
3D all the way: Semantic segmentation of urban scenes from start to end in 3D
Author :
Anđelo Martinović;Jan Knopp;Hayko Riemenschneider;Luc Van Gool
Author_Institution :
KU Leuven, 3000, Belgium
fDate :
6/1/2015 12:00:00 AM
Abstract :
We propose a new approach for semantic segmentation of 3D city models. Starting from an SfM reconstruction of a street-side scene, we perform classification and facade splitting purely in 3D, obviating the need for slow image-based semantic segmentation methods. We show that a properly trained pure-3D approach produces high quality labelings, with significant speed benefits (20x faster) allowing us to analyze entire streets in a matter of minutes. Additionally, if speed is not of the essence, the 3D labeling can be combined with the results of a state-of-the-art 2D classifier, further boosting the performance. Further, we propose a novel facade separation based on semantic nuances between facades. Finally, inspired by the use of architectural principles for 2D facade labeling, we propose new 3D-specific principles and an efficient optimization scheme based on an integer quadratic programming formulation.
Keywords :
"Three-dimensional displays","Labeling","Semantics","Solid modeling","Grammar","Optimization","Bismuth"
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2015.7299075