4-points congruent sets for robust pairwise surface registration

By Dror Aiger, Niloy J. Mitra, Daniel Cohen-Or. ACM Transactions on Graphics, 2008

866 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/4d67165ad887e66c2130b40b39b262c9759298e6

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

In Geology

Citations in the corpus

Robust reconstruction of indoor scenes (2015, background): “In the past decade researchers have studied local shape descriptors that can be used for pruning and correspondence [20] [52] [55] [24], and proposed different types of constellations [2] [16] [43].”
Data-driven suggestions for creativity support in 3D modeling (2010, methodology): “Our implementation uses the 4-PCS algorithm with 1000 iterations [Aiger et al. 2008].”
Fast Global Registration (2016, methodology): “Some pipelines use point-to-point matches based on local geometric descriptors [16, 40], others define correspondences on pairs or tuples of points [1, 8, 26, 29].”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, methodology): “In medical image registration, surface matching methods often use surface coordinates or geometric features extracted from anatomical structures [2, 26, 47, 57].”
Voronoi-Based Curvature and Feature Estimation from Point Clouds (2011, background): “…are rotation-invariant local descriptors, which together with principal curvature directions have proven useful in detecting structural regularity [PMW + 08], global matching [AMCO08], modeling and rendering of point-based surfaces [GTE + 06], and anisotropic smoothing [LP05] to name just a few.”
Deep Global Registration (2020, methodology): “A widely used family of techniques for robust model ﬁtting is based on RANdom SAmple Consensus (RANSAC) [38, 1, 35, 29, 19], which iteratively samples small sets of correspondences in the hope of sampling a subset that is free from outliers.”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, background): “While other surveys exist, our speciﬁc contributions include the following: Rigid and Non-Rigid Registration: Our survey covers registrations over the past two decades.”
M2DP: A novel 3D point cloud descriptor and its application in loop closure detection (2016, methodology): “For recovering larger motion between two point clouds, one can resort to the 4-Points Congruent Sets (4PCS) [4], the Super-4PCS [5], the Congruent Pyramids method [7] and the 2D-3PCS [6].”
3DMatch: Learning the Matching of Local 3D Geometry in Range Scans (2016, background): “By default, these depth maps are not aligned to any global coordinate system, and for our purposes, we do not use any color information – focusing only on the information available from the depth channels.”
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions (2016, methodology): “int Cloud Library [3]. A popular state-of-theart method in PCL is point feature histograms (PFH), which are based on the relationship of all surface normals and curvature estimates [26]. Aiger et al. [2] show that pairs of fragments can be aligned by ﬁnding sets of four congruent points (4PCS); Mell”
Fast and Robust Iterative Closest Point (2020, background): “Aiger et al. [20] aligned two point clouds by matching a pair of co-planar 4-point sets from them that are approximately congruent.”
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency (2021, background): “, [8, 1, 47, 31, 44, 44]) have been comprehensively reviewed in [52].”