Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion

393 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, methodology): “The MVS method takes images along with their camera positions estimated by Global SFM [50] and outputs the reconstructed model.”
A Survey on Structure from Motion (2017, methodology): “…is given in [53], where this time, instead of using a cost function given as the sum of squared errors (as in [76]) or the maximum error (as in [49]) in the system of equations (16), the method minimizes the sum of unsquared errors in (16) (hence the name least unsquared deviations (LUD)…”
Robust Global Translations with 1DSfM (2014, methodology): “Our method for outlier removal is similar in motivation to [18], but by projecting into a single dimension we solve tractable subproblems that reduce to a simple combinatorial graph problem.”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, background): “Subsequently, other different perspectives for solving the problem including factorization [151, 154] and rotation averaging [50, 107] appeared.”
OpenMVG: Open Multiple View Geometry (2016, methodology): “- Translation averaging with L2 norm [17], L1, and L∞ [5].”