DocumentCode :
2919028
Title :
Active learning for piecewise planar 3D reconstruction
Author :
Kowdle, Adarsh ; Chang, Yao-Jen ; Gallagher, Andrew ; Chen, Tsuhan
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
929
Lastpage :
936
Abstract :
This paper presents an active-learning algorithm for piecewise planar 3D reconstruction of a scene. While previous interactive algorithms require the user to provide tedious interactions to identify all the planes in the scene, we build on successful ideas from the automatic algorithms and introduce the idea of active learning, thereby improving the reconstructions while considerably reducing the effort. Our algorithm first attempts to obtain a piecewise planar reconstruction of the scene automatically through an energy minimization framework. The proposed active-learning algorithm then uses intuitive cues to quantify the uncertainty of the algorithm and suggest regions, querying the user to provide support for the uncertain regions via simple scribbles. These interactions are used to suitably update the algorithm, leading to better reconstructions. We show through machine experiments and a user study that the proposed approach can intelligently query users for interactions on informative regions, and users can achieve better reconstructions of the scene faster, especially for scenes with texture-less surfaces lacking cues like lines which automatic algorithms rely on.
Keywords :
image reconstruction; learning (artificial intelligence); minimisation; active-learning algorithm; automatic algorithms; energy minimization framework; piecewise planar 3D reconstruction; texture-less surfaces; Image reconstruction; Labeling; Minimization; Surface reconstruction; Surface texture; Three dimensional displays; Uncertainty;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
ISSN :
1063-6919
Print_ISBN :
978-1-4577-0394-2
Type :
conf
DOI :
10.1109/CVPR.2011.5995638
Filename :
5995638
Link To Document :
بازگشت