Efficient variants of the ICP algorithm

By Szymon Rusinkiewicz, Marc Levoy. Proceedings Third International Conference on 3-D Digital Imaging and Modeling, 2001

4,791 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Geology

View Paper: https://www.semanticscholar.org/paper/19d4da2841588fc75ccedcfb443d73772413d98e

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 Geology

Citations in the corpus

An evaluation of the RGB-D SLAM system (2012, background): “(ICP) algorithm [2], [26], [27] for aligning pairs of local point clouds to establish constraints between observations.”
Möbius voting for surface correspondence (2009, methodology): “Although it has more commonly been used for registration of rigid surfaces [Rusinkiewicz and Levoy 2001], ICP has also been applied for large number of non-rigid deformation problems [Allen et al. 2003; Bronstein et al. 2006; Brown and Rusinkiewicz 2007; Huang et al. 2008; Pauly et al. 2005].”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, background): “Among all the existing surveys (Table 1), [11]–[15] focus on rigid registration only.”
Factorized Graph Matching (2016, background): “There have been various strategies proposed to address this issue [50].”
Deep Closest Point: Learning Representations for Point Cloud Registration (2019, methodology): “For more information, [32, 37] summarize ICP and its variants developed over the last 20 years.”
Geometrically stable sampling for the ICP algorithm (2003, methodology): “The two techniques that are the most similar to our approach are those of Simon [12] and Rusinkiewicz [11].”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, background): “…as a least squared error of point-to-point distances: Emodel→data(θ,D) = ∑ i ‖vi(θ)−Xi‖2 (6) An alternative to the point-to-point distance is the pointto-plane distance, which is commonly used for 3D reconstruction (Chen and Medioni, 1991; Rusinkiewicz and Levoy, 2001; Rusinkiewicz et al, 2002).”
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet (2019, background): “Unlike many variants of iterative closest point (ICP), our approach requires no costly computation of point correspondences [31], which gives rise to substantial advantages in terms of accuracy, robustness to initialization and computational efficiency.”
Fast and Robust Iterative Closest Point (2020, background): “One popular approach is to disregard erroneous correspondence between points, using heuristics based on their distance or the angle between their normals [5].”
Fully Automatic Registration of 3D Point Clouds (2006, methodology): “The golden standard for ﬁne registration is the Iterative Closest Point algorithm [4] and its variants [24].”
Static and dynamic 3D facial expression recognition: A comprehensive survey (2012, background): “Many variants of ICP have also been proposed, and the interested reader may refer to the following [70–72].”
PRNet: Self-Supervised Learning for Partial-to-Partial Registration (2019, methodology): “ICP [5] and variants [6, 7, 8, 9] have been widely used for registration.”
Accuracy analysis of kinect depth data (2012, methodology): “The characterization of random errors is important and useful in further processing of the depth data, for example in weighting the point pairs in the registration algorithm (Rusinkiewicz and Levoy, 2001).”