Visibility Probability Structure from SfM Datasets and Applications

Siddharth Choudhary, P J Narayanan

Center for Visual Information Technology, IIIT Hyderabad, India


Seed Point

First Match

Second Match

Third Match

Fourth Match

Abstract

Large scale reconstructions of camera matrices and point clouds have been created using structure from motion from community photo collections. Such a dataset is rich in information; it represents a sampling of the geometry and appearance of the underlying space. In this paper, we encode the visibility information between and among points and cameras as visibility probabilities. The conditional visibility probability of a set of points on a point (or a set of cameras on a camera) can rank points (or cameras) based on their mutual dependence. We combine the conditional probability with a distance measure to prioritize points for fast guided search for the image localization problem. We define dual problem of feature triangulation as finding the 3D coordinates of a given image feature point. We use conditional visibility probability to quickly identify a subset of cameras in which a feature is visible.

Citation

Downloads


Datasets

The datasets used in this work are from the Location recognition project by Li et al.

Acknowledgements

This work was partly supported by the Indian Digital Heritage project of DST. We thank Noah Snavely for the datasets and Torsten Sattler for insightful discussions over email.

Contact

Send any comments or questions to Siddharth Choudhary (Email : siddharth [dot] choudhary [at] gatech.edu)