1dsfm (18 files)
SfM_Init-master.zip 38.05kB
images.Yorkminster.tar 2.30GB
images.Union_Square.tar 3.80GB
images.Vienna_Cathedral.tar 3.45GB
1DSfM_ECCV14.pdf 11.61MB
images.Roman_Forum.tar 1.59GB
images.Tower_of_London.tar 1.08GB
images.Piccadilly.tar 3.97GB
images.NYC_Library.tar 1.69GB
images.Piazza_del_Popolo.tar 1.52GB
images.Montreal_Notre_Dame.tar 1.63GB
images.Madrid_Metropolis.tar 740.75MB
images.Ellis_Island.tar 1.62GB
images.Gendarmenmarkt.tar 1.03GB
datasets.tar.gz 682.12MB
images.Alamo.tar 2.09GB
images.Trafalgar.tar 9.11GB
1DSfM_poster.pdf 25.82MB
Type: Dataset
Tags: Dataset, photos, structure from motion, landmark, cornell, photo, paper, code, photographs, sfm

Bibtex:
@inproceedings{wilson_eccv2014_1dsfm,
title= {1dsfm},
author= {Kyle Wilson and Noah Snavely},
booktitle= {Proceedings of the European Conference on Computer Vision ({ECCV})},
year= {2014},
abstract= {We present a simple, effective method for solving structure from motion problems by averaging epipolar geometries. Based on recent successes in solving for global camera rotations using averaging schemes, we focus on the problem of solving for 3D camera translations given a network of noisy pairwise camera translation directions (or 3D point observations). To do this well, we have two main insights. First, we propose a method for removing outliers from problem instances by solving simpler low-dimensional subproblems, which we refer to as 1DSfM problems. Second, we present a simple, principled averaging scheme. We demonstrate this new method in the wild on Internet photo collections. 

Dataset scraped 23 February 2019

Code and papers scraped 15 July 2022},
keywords= {Dataset, photos, structure from motion, landmark, cornell, photo, paper, code, photographs, sfm},
terms= {},
license= {},
superseded= {},
url= {https://research.cs.cornell.edu/1dsfm/}
}


Send Feedback