SBA: A software package for generic sparse bundle adjustment

By Manolis I. A. Lourakis, Antonis A. Argyros. TOMS, 2009

977 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/79492593b0936714d5cc6db9339d5a486e6e77db

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 Computer Vision and Pattern Recognition

Citations in the corpus

Structure-from-Motion Revisited (2016, methodology): “Exact methods solve the system by storing and factoring it as a dense or sparse matrix [13, 38] with a space complexity of O(N(2) P ) and a time complexity of O(N 3 P ).”
Light-weight localization for vehicles using road markings (2013, methodology): “We use a windowed bundle adjustment to smooth the noise due to visual odometry, for which purpose we use the sparse bundle adjustment algorithm [12].”
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics (2015, methodology): “Sparse Bundle Adjustment (SBA) [76] was also applied in order to obtain a globally consistent map and loop closure was detected by matching the current frame to previously collected key-frames.”
Global Motion Estimation from Point Matches (2012, methodology): “• Bundle adjustment and dense 3D recovery: We used the SBA code by [23] for the smaller sets and PBA [24] for the larger sets.”
Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes (2014, methodology): “The shape and motion parameters are then refined using the sparse implementation of bundle adjustment [19].”
High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth (2014, methodology): “We then reproject the resulting points back into 3D using the initial calibration parameters, and perform sparse bundle adjustment using SBA [23] to minimize the residual y-disparities.”
Bundle Adjustment in the Large (2010, background): “The basic mathematics of the bundle adjustment problem are well understood [4], and there is also a freely available high-quality implementation – SBA [5].”
Towards Linear-Time Incremental Structure from Motion (2013, methodology): “One impressive example of this algorithm is Lourakis and Argyros’ SBA [9] used by Photo Tourism [14].”
Geometry-Aware Learning of Maps for Camera Localization (2017, methodology): “Similarly, bundle adjustment [36, 54] has also been a popular choice for methods using structure from motion techniques (i.”
Building Rome in a day (2009, methodology): “The best performing BA software available publicly is Sparse Bundle Adjustment (SBA) by Lourakis & Argyros [9].”
RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments (2012, methodology): “We show that globally consistent alignments can be achieved either via highly efficient pose graph optimization such as TORO (Lu and Milios 1997; Konolige 2004; Thrun et al. 2005; Grisetti et al. 2007a) or via sparse bundle adjustment (Lourakis and Argyros 2009; Konolige 2010b).”
Real-time monocular SLAM: Why filter? (2010, methodology): “For BA, we employ the well known high-performance SBA library [16].”
An evaluation of the RGB-D SLAM system (2012, methodology): “use sparse bundle adjustment [19] for the optimization of the 2.”
G2o: A general framework for graph optimization (2011, methodology): “Typical instances are simultaneous localization and mapping (SLAM) [19], [5], [22], [10], [16], [26] or bundle adjustment (BA) [27], [15], [18].”
Photometric Bundle Adjustment for Dense Multi-view 3D Modeling (2014, methodology): “This is known as Geometric Bundle Adjustment (BA) [21, 13], and has been successfully applied to various sparse 3D reconstruction scenari, mostly minimizing a Geometric Reprojection Error:”
A Survey on Structure from Motion (2017, methodology): “Essentially, bundler is based on an incremental application of a modiﬁed version of the sparse bundle adjustment (SBA) package of [41], and, being an incremental method, it incorporates a few images at a time to produce a camera motion and a 3D structure estimate from a set of images, image…”