PAIGE: PAirwise Image Geometry Encoding for Improved Efficiency in Structure-From-Motion

Johannes L. Schonberger, Alexander C. Berg, Jan-Michael Frahm; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1009-1018

Abstract


Large-scale Structure-from-Motion systems typically spend major computational effort on pairwise image matching and geometric verification in order to discover connected components in large-scale, unordered image collections. In recent years, the research community has spent significant effort on improving the efficiency of this stage. In this paper, we present a comprehensive overview of various state-of-the-art methods, evaluating and analyzing their performance. Based on the insights of this evaluation, we propose a learning-based approach, the PAirwise Image Geometry Encoding (PAIGE), to efficiently identify image pairs with scene overlap without the need to perform exhaustive putative matching and geometric verification. PAIGE achieves state-of-the-art performance and integrates well into existing Structure-from-Motion pipelines.

Related Material


[pdf]
[bibtex]
@InProceedings{Schonberger_2015_CVPR,
author = {Schonberger, Johannes L. and Berg, Alexander C. and Frahm, Jan-Michael},
title = {PAIGE: PAirwise Image Geometry Encoding for Improved Efficiency in Structure-From-Motion},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}