A new point matching algorithm for non-rigid registration

By Haili Chui, Anand Rangarajan. 2003

1,728 citations recorded by the source corpus.

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

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

An Algorithmic Perspective on Imitation Learning (2018, methodology): “Although the original work on trajectory transfer with nonrigid registration employed the thin plate spline robust point matching (TPS-RPM) approach proposed in [Chui and Rangarajan, 2003], the framework is not limited to specific non-rigid registration methods. The recent work by Lee et al. [2015b]”
Zero-Shot Visual Imitation (2018, methodology): “The matching cost is measured using the thin plate spline robust point matching technique (TPS-RPM) described in (Chui & Rangarajan, 2003).”
A case study of trajectory transfer through non-rigid registration for a simplified suturing scenario (2013, methodology): “We use the method of Thin Plate Spline Robust Point Matching [1] to find both their correspondences, encoded by an index-mapping function Π(·) (which maps from indices of points in demonstration scene to indices of points in the test scene) and a warping function f mapping x1,x2, . . . ,xK to their ”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “The robust point matching (RPM) algorithm (Gold et al. 1998) are proposed to overcome the ICP limitations; the soft assignment and deterministic annealing strategy are adopted, and the rigid transformation model is generalized to a non-rigid one by using the thin-plate spline [TPS-RPM (Chui and Rang”
Shape matching and object recognition using low distortion correspondences (2005, background): “Another approach is the non-rigid point matching of [6] based on thin plate splines and “softassign”.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation (2011, neutral): “Few exceptions in registration where correspondences are automatically computed can be found in [13], [35].”
Point Set Registration: Coherent Point Drift (2009, methodology): “We test CPD against TPS-RPM [9] on synthentically generated 2D fish non-rigid examples with respect to a) level of non-rigid deformation, b) amount of noise in the point sets locations c) number of outliers.”
Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm (2005, neutral): “A u t h o r ' s p e r s o n a l”
Learning from Demonstrations Through the Use of Non-rigid Registration (2013, methodology): “This appendix describes our registration procedure, which is based of the TPS-RPM algorithm of Chui and Ragnarajan [19].”
Deformable Medical Image Registration: A Survey (2013, neutral): “[339].”
Shape Matching and Object Recognition (2006, methodology): “Another approach is the non-rigid point matching of [Chui and Rangarajan, 2003] based on thin plate splines and “softassign”.”
Tracking deformable objects with point clouds (2013, background): “Chui and Rangarajan [4] alternated fitting a non-rigid transformation with a soft-assignment correspondence calculation.”
Robust 3D Shape Correspondence in the Spectral Domain (2006, methodology): “TPS-RPM [6] failed by rotation. pose changes in the models or when the models consist of a large number of articulated subparts.”