Sparse Iterative Closest Point

By Sofien Bouaziz, Andrea Tagliasacchi, Mark Pauly. Eurographics Symposium on Geometry Processing, 2013

543 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/53b787c284085c774c564a0e7c88f79927ebd143

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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Global Convergence of ADMM in Nonconvex Nonsmooth Optimization (2015, background): “Indeed, the nonconvex case of the problem (1) has found wide applications in, for example, matrix completion and separation [73,72,77,54,57], asset allocation [65], tensor factorization [35], phase retrieval [66], compressive sensing [10], optimal power flow [74], direction fields correction [32], n”
Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection (2019, unknown): “[39] propose robust variants of the iterative closest point algorithm for P-REG.”
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning (2020, unknown): “This problem can be addressed via smooth (IRLS) or combinatorial (RANSAC) optimization – both methods can be interpreted in terms of sparse optimization, such that inliers and outliers are clustered separately; see [7].”
Deep Global Registration (2020, methodology): “Other methods use robust loss functions to reject outliers during optimization [50, 4].”
Fast Global Registration (2016, background): “Average # of points PCL ICP point-to-point PCL ICP point-to-plane Sparse ICP point-to-point [5] Sparse ICP point-to-plane [5] Our approach”
Deep Closest Point: Learning Representations for Point Cloud Registration (2019, background): “ICP variants [37, 40, 6] consider issues with the basic method, like noise, partiality, and sparsity; probabilistic models [2, 15, 19] also can improve resilience to uncertain data.”
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.”
NASA: Neural Articulated Shape Approximation (2019, unknown): “This approximation is suitable for tracking, as large values of distance should be associated with outliers in a registration optimization [6], and therefore ignored.”
Colored Point Cloud Registration Revisited (2017, unknown): “[2].”
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet (2019, background): “Several variants of the ICP have been developed (see [31] for a review) that incorporate sensor uncertainties [33, 35], are robust to outliers [5], use different optimizers [8], etc.”
GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (2021, unknown): “As for depth-based methods, the Iterative Closest Point (ICP) algorithm [72] and its variants [73], [74], [75], [76], [77] stand out as the predominant traditional pose reﬁnement algorithms.”
A comprehensive survey on point cloud registration (2021, unknown): “Given correspondences, the SVD-based estimation methods [6], [90], [9], [106], [7] perform singular value decomposition (SVD) to the difference of correspondences.”
Fast and Robust Iterative Closest Point (2020, methodology): “It was observed in [6] that such methods can be difﬁcult to tune or increase the number of local minima.”
TEASER: Fast and Certifiable Point Cloud Registration (2020, background): “Multiple variants of ICP [62], [63], [64], [65], [66], [67], [68] have proposed to use robust cost functions to improve convergence.”
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration (2016, background): “It may also be extended to ICP variants with Lp-norms [66], such as the robustness-promoting L1-norm.”