View-graph is an essential input to large-scale structure from motion (SfM) pipelines. Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph. Inconsistent or inaccurate edges can lead to inferior or wrong reconstruction. Most SfM methods remove `undesirable' images and pairs using several, fixed heuristic criteria, and propose tailor-made solutions to achieve specific reconstruction objectives such as efficiency, accuracy, or disambiguation. In contrast to these disparate solutions, we propose a single optimization framework that can be used to achieve these different reconstruction objectives with task-specific cost modeling. We also construct a very efficient network-flow based formulation for its approximate solution. The abstraction brought on by this selection mechanism separates the challenges specific to datasets and reconstruction objectives from the standard SfM pipeline and improves its generalization. This paper demonstrates the application of the proposed view-graph framework with standard SfM pipeline for two particular use-cases, (i) accurate and ghost-free reconstructions of highly ambiguous datasets using costs based on disambiguation priors, and (ii) accurate and efficient reconstruction of large-scale Internet datasets using costs based on commonly used priors.
[1]
Robert T. Collins,et al.
Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow
,
2013,
2013 IEEE Conference on Computer Vision and Pattern Recognition.
[2]
Jan-Michael Frahm,et al.
Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction
,
2014,
ECCV.
[3]
Richard Szeliski,et al.
Structure from motion for scenes with large duplicate structures
,
2011,
CVPR 2011.
[4]
Noah Snavely,et al.
Robust Global Translations with 1DSfM
,
2014,
ECCV.
[5]
Wolfram Burgard,et al.
Robust Visual Robot Localization Across Seasons Using Network Flows
,
2014,
AAAI.
[6]
Steven M. Seitz,et al.
Photo tourism: exploring photo collections in 3D
,
2006,
ACM Trans. Graph..
[7]
Daniel P. Huttenlocher,et al.
Location Recognition Using Prioritized Feature Matching
,
2010,
ECCV.
[8]
David K. Smith.
Network Flows: Theory, Algorithms, and Applications
,
1994
.
[9]
Venu Madhav Govindu,et al.
Efficient and Robust Large-Scale Rotation Averaging
,
2013,
2013 IEEE International Conference on Computer Vision.
[10]
Ravindra K. Ahuja,et al.
Network Flows: Theory, Algorithms, and Applications
,
1993
.