Bundle Adjustment in the Large

By Sameer Agarwal, Noah Snavely, S. M. Seitz, Richard Szeliski. European Conference on Computer Vision, 2010

561 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8d0d3cc477265f14e71507fb060cb64055b52a48

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

A constant-time SLAM back-end in the continuum between global mapping and submapping: application to visual stereo SLAM (2016, methodology): “…2008; Kaess et al. 2011), due to new advances in sparse algebra (e.g. sparse Cholesky decomposition (Davis 2006), inexact Newton type algorithms (Agarwal et al. 2010)), becoming a promising alternative to ﬁltering methods extensively employed for SLAM during previous years (Strasdat et al.…”
A Survey of Urban Reconstruction (2013, methodology): “In various projects this information has been recognized as a valuable source for large scale urban reconstruction [SSS06,IZB07,ASSS10,FFGG ∗ 10].”
BA-Net: Dense Bundle Adjustment Network (2018, methodology): “We only introduce the most relevant content and refer the readers to Triggs et al. (2000) and Agarwal et al. (2010) for a comprehensive introduction.”
Multicore bundle adjustment (2011, methodology): “In [1], the authors show how to evaluate Spc without forming S explicitly.”
A Survey on Structure from Motion (2017, methodology): “In more detail, [1] considers a nonlinear least squares 14 bundle adjustment problem stated (abstractly) as minimize where x ∈ R p , F : R p → R q .”
Automated Crack Detection on Concrete Bridges (2016, methodology): “The best way to avoid this is a procedure called bundle adjustment [40]–[42] which computes all of the interframe homographies in a global optimization over all relevant images.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, unknown): “The computer vision expert may notice a resemblance between problem (5) and bundle adjustment (BA) in Structure from Motion [275]; both (5) and BA indeed stem from a maximum-a-posteriori formulation.”
Structure-from-Motion Revisited (2016, background): “While sparse direct methods reduce the complexity by a large factor for sparse problems, they are prohibitive for large unstructured photo collections due to typically much denser connectivity graphs [54, 4].”
SfM with MRFs: Discrete-Continuous Optimization for Large-Scale Structure from Motion (2013, unknown): “, from a laser scanner), but it is difficult to collect this data for the scale of scenes that we consider here (and for this reason most papers do not attempt quantitative evaluations [3], [5], [10]).”
Continuous 3D Perception Model with Persistent State (2025, unknown): “Notable examples include traditional methods such as Structure from Motion (SfM) [1, 2, 28, 47, 65, 66, 70, 71, 80] and Simultaneous Localization and Mapping (SLAM) [11, 16, 19, 22, 37, 51, 53], as well as more recent approaches such as Neural Radiance Fields (NeRF) [12, 24, 49, 50, 84] and 3D…”
G2o: A general framework for graph optimization (2011, background): “There are also new systems based on nonlinear conjugate gradient that never form the linear system explicitly [1], [2]; these converge more slowly, but can work with extremely large datasets (∼1000M matrix elements).”
Towards Linear-Time Incremental Structure from Motion (2013, methodology): “By using only the O(n) space Hessian matrices and avoiding the Schur complement, the CG iteration has achieved O(n) time complexity [1, 3].”
Tanks and temples (2017, methodology): “…the great successes of visual computing, combining rigorous theory [Hartley and Zisserman 2000; Triggs et al. 2000], advanced computational methods [Agarwal et al. 2010; Furukawa and Hernández 2015; Wu et al. 2011], and a culture of open software development [Fuhrmann et al. 2015; Furukawa 2011;…”