DocumentCode :
2918797
Title :
Discrete-continuous optimization for large-scale structure from motion
Author :
Crandall, David ; Owens, Andrew ; Snavely, Noah ; Huttenlocher, Dan
Author_Institution :
Indiana Univ., Bloomington, IN, USA
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
3001
Lastpage :
3008
Abstract :
Recent work in structure from motion (SfM) has successfully built 3D models from large unstructured collections of images downloaded from the Internet. Most approaches use incremental algorithms that solve progressively larger bundle adjustment problems. These incremental techniques scale poorly as the number of images grows, and can drift or fall into bad local minima. We present an alternative formulation for SfM based on finding a coarse initial solution using a hybrid discrete-continuous optimization, and then improving that solution using bundle adjustment. The initial optimization step uses a discrete Markov random field (MRF) formulation, coupled with a continuous Levenberg-Marquardt refinement. The formulation naturally incorporates various sources of information about both the cameras and the points, including noisy geotags and vanishing point estimates. We test our method on several large-scale photo collections, including one with measured camera positions, and show that it can produce models that are similar to or better than those produced with incremental bundle adjustment, but more robustly and in a fraction of the time.
Keywords :
Markov processes; cameras; image motion analysis; optimisation; random processes; solid modelling; 3D models; Internet; MRF formulation; camera positions; continuous Levenberg-Marquardt refinement; discrete Markov random field formulation; hybrid discrete-continuous optimization; incremental algorithms; incremental bundle adjustment; incremental techniques; large-scale photo collections; large-scale structure from motion; noisy geotags; unstructured collections; vanishing point estimates; Cameras; Equations; Image reconstruction; Noise measurement; Optimization; Robustness; Three dimensional displays;
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.2011.5995626
Filename :
5995626
Link To Document :
بازگشت