Network Principles for SfM: Disambiguating Repeated Structures with Local Context
Abstract:
|
|
Repeated features are common in urban scenes. Many objects, such as
clock towers with nearly identical sides, or domes with strong radial
symmetries, pose challenges for structure from motion. When similar but
distinct features are mistakenly equated, the resulting 3D reconstructions
can have errors ranging from phantom walls and superimposed structures to a
complete failure to reconstruct. We present a new approach to solving such
local visibility structure of such repeated features. Drawing upon
network theory, we present a new way of scoring features using a measure of
local clustering. Our model leads to a simple, fast, and highly scalable
technique for disambiguating repeated features based on an analysis of an
underlying visibility graph, without relying on explicit geometric reasoning.
We demonstrate our method on several very large datasets drawn from Internet
photo collections, and compare it to a more traditional geometry-based
disambiguation technique.
|
Downloads
--- Update 2 May 2017 ---
Bugfix: The k-cover code
implementation now conforms to the algorithm
description in the paper. Thanks to Derek Hoiem for
noticing the discrepancy! ---
--- Update 27 July 2014 ---
The dataset files below have been updated to include missing README files, and to replace all EG.txt files. These were included for possible reference and are not required to run our code. They were previously miscomputed, but are now correct. ---
The datasets in the paper are available in two downloads: the matches and tracks used as input for disambiguation and reconstruction, and the original images. The images are not necessary to run the code.
 |
Full Paper ICCV2013
|
| PDF (13MB) |
|
 |
Poster ICCV2013
|
| PDF (13MB) |
|
 |
Code
MATLAB code used to generate results in the paper.
|
| Github |
|
 |
Dataset
Matches and tracks for Seville
|
| tar.gz (71MB) |
|
 |
Dataset
Images for Seville
|
| tar.gz (1.6GB) |
|
 |
Dataset
Matches and tracks for SacreCoeur
|
| tar.gz (263MB) |
|
 |
Dataset
Images for SacreCoeur
|
| tar.gz (3.1GB) |
|
 |
Dataset
Matches and tracks for Louvre
|
| tar.gz (37MB) |
|
 |
Dataset
Images for Louvre
|
| tar.gz (3.5GB) |
|
 |
Dataset
Matches and tracks for NotreDame
|
| tar.gz (898MB) |
|
 |
Dataset
Images for NotreDame
|
| tar.gz (8.0GB) |
|
BibTeX entry
@inproceedings{wilson_iccv2013_disambig,
Title = {Network Principles for SfM: Disambiguating Repeated Structures with Local Context}
Author = {Kyle Wilson and Noah Snavely},
booktitle = {Proceedings of the International
Conference on Computer Vision ({ICCV})},
Year = {2013},
}
Acknowledgments.This work was supported in part by the National
Science Foundation under IIS-1149393, IIS-1111534, and IIS-0964027, and a grant
from Intel Corporation. We would also like to thank Chun-Po Wang and Robert
Kleinberg for their valuable discussions.