Robust Registration of 2D and 3D Point Sets

By Andrew William Fitzgibbon. British Machine Vision Conference, 2003

1,103 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/93bd95d97543031e39d524ed408a543d740d4eb5

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

Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “Numerous studies, such as EM-ICP (Granger and Pennec 2002), LM-ICP (Fitzgibbon 2003), and TriICP (Chetverikov et al.”
A comprehensive survey on point cloud registration (2021, methodology): “LM-ICP [32] leverages the Levenberg-Marquardt algorithm to estimate the transformation by adding a damping factor to the original LK algorithm.”
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration (2016, methodology): “Next, we will introduce the concept of an uncertainty radius as a mathematical preparation, then derive our bounds based on it.”
Robust semantic analysis by synthesis of 3D facial motion (2011, methodology): “Our fitting process, which is similar to [14], uses these closest points between the 3DMM-PCA and the data in a robust Fig.”
3-D Mapping With an RGB-D Camera (2014, methodology): “To compute the relative motion between observations, most state-of-the-art SLAM (and also localization only) systems use variants of the ICP algorithm [2]–[4].”
Towards 3D Point cloud based object maps for household environments (2008, methodology): “Furthermore, methods for generating initial approximate alignments [10,35,19], as well as choosing alternate optimization methods [14,6], improved the results of the registration process.”
Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes (2012, methodology): “To speed up point-to-point matching, we use the efficient voxel-based ICP method of [28], which relies on a grid that can be pre-computed for each object.”
Aligning point cloud views using persistent feature histograms (2008, background): “narrow convergence basin, several alternative optimization methods have been proposed [18], [19], though they require that the individual point cloud data views are already roughly aligned with each other.”
Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior (2005, methodology): “The difference between the Fitzgibbon algorithm and this one, is that in [8], only the rigid parameters were estimated.”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, neutral): “More efficient solutions than ICP were proposed in [40], [112].”
Finding nemo: Deformable object class modelling using curve matching (2010, background): “We then summarize our contributions (§6) and discuss shortcomings and future directions.”
Shape context and chamfer matching in cluttered scenes (2003, methodology): “Fitzgibbon [8] introduced a versionof theICP algorithm which combinesthecorresponde nceand the alignment stepswithin the structureof the LevenbergMarquardtalgorithm.”
Neural Unsigned Distance Fields for Implicit Function Learning (2020, methodology): “They are used for shape registration [26], model fitting [69, 3], to speed up inference in part based models [25], and for extracting skeletons and medial axis [22, 8].”
PRNet: Self-Supervised Learning for Partial-to-Partial Registration (2019, methodology): “Another trend is to improve the optimization: [13] applies Levenberg—Marquardt to the ICP objective, while global methods seek a solution using branch-and-bound [14], Riemannian optimization [15], convex relaxation [16], mixed-integer programming [17], and semideﬁnite programming [18].”
Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm (2005, methodology): “For example, a recent paper by Fitzgibbon [9] presents an attempt of minimisation of the MSE cost function using the Levenberg-Marquardt algorithm.”