3,381 Hits in 5.3 sec

Non-Rigid Point Set Registration Networks [article]

Lingjing Wang, Jianchun Chen, Xiang Li, Yi Fang
2019 arXiv   pre-print
PR-Net achieves robust and superior performance for non-rigid registration of point sets, even in presence of Gaussian noise, outliers, and missing points, but requires much less time for registering large  ...  Point set registration is defined as a process to determine the spatial transformation from the source point set to the target one.  ...  Experimental Setup: We conduct tests to compare PR-Net with the non-learning based approach. Coherent Point Drifts (CPD) [28] is a highly recognized non-rigid point set registration method.  ... 
arXiv:1904.01428v1 fatcat:cxonx4a4wjhsvnfqybw3i5lf6a

Point Set Registration: Coherent Point Drift

Andriy Myronenko, Xubo Song
2010 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We introduce a probabilistic method, called the Coherent Point Drift (CPD) algorithm, for both rigid and non-rigid point set registration.  ...  Multiple factors, including an unknown non-rigid spatial transformation, large dimensionality of point set, noise and outliers, make the point set registration a challenging problem.  ...  Non-rigid alignment of 3D surfaces using its control points: blue onto red. =⇒ CONCLUSIONS We introduce Coherent Point Drift (CPD), a new probabilistic method for non-rigid point set registration.  ... 
doi:10.1109/tpami.2010.46 pmid:20975122 fatcat:q7jwgshwmncxdalqvpqn3nlj5u

Non-rigid point set registration: A bidirectional approach

Qiang Sang, Jianzhou Zhang, Zeyun Yu
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper we present a novel point set registration algorithm based on the robust Gaussian Mixture Model(GMM). We take advantage of a robust estimation to weigh the noise component in GMM.  ...  Moreover, a bidirectional EM process is introduced to model outliers in both point sets in contrast to traditional methods.  ...  The non-rigid point set registration method is proposed in Section 2.  ... 
doi:10.1109/icassp.2012.6287978 dblp:conf/icassp/SangZY12 fatcat:r7w5exjnurbzxpausbbyivngzm

GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor [article]

Lingjing Wang, Xiang Li, Yi Fang
2020 arXiv   pre-print
In this paper, we propose a novel method named GP-Aligner to deal with the problem of non-rigid groupwise point set registration.  ...  GP-Aligner shows both accuracy and computational efficiency improvement in comparison with state-of-the-art methods for groupwise point set registration.  ...  As a classical non-parametric method, coherence point drift (CPD) was proposed by Myronenko et al.  ... 
arXiv:2007.12979v1 fatcat:y5uihazcmnebldt2ddqzqy2b7m

Non-rigid point set registration via coherent spatial mapping

Jun Chen, Jiayi Ma, Changcai Yang, Li Ma, Sheng Zheng
2015 Signal Processing  
In this paper, we proposed a new point set registration method based on coherent spatial mapping (CSM), whose solution is formulated as a maximum likelihood problem.  ...  Point set registration is essential for many computer vision technologies.  ...  Algorithm 2 . 2 Non-rigid point set registration.  ... 
doi:10.1016/j.sigpro.2014.07.004 fatcat:npta63nf4fec7guts4ah4ctcg4

LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration [article]

Weixiao Liu, Hongtao Wu, Gregory Chirikjian
2021 arXiv   pre-print
In this paper, we propose a novel method called CPD with Local Surface Geometry (LSG-CPD) for rigid point cloud registration.  ...  In the M step, we perform an unconstrained optimization on a matrix Lie group to efficiently update the rigid transformation of the registration.  ...  Future works include extending the current framework to non-rigid registration and applying the method to more computer vision tasks, e.g., pose estimation and SLAM.  ... 
arXiv:2103.15039v2 fatcat:japqyywsfzhbtl2ims7zm4nw7i

Non-rigid articulated point set registration with Local Structure Preservation

Song Ge, Guoliang Fan
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We propose a new Gaussian mixture model (GMM)based probabilistic point set registration method, called Local Structure Preservation (LSP), which is aimed at complex non-rigid and articulated deformations  ...  The registration is formulated as a density estimation problem where the LLE and LC terms are embedded in the GMM-based Coherent Point Drift (CPD) framework.  ...  Coherent Point Drift (CPD) [16, 15] is an effective GMM-based non-rigid registration algorithm that imposes a coherence constraint to preserve the topology of the point sets.  ... 
doi:10.1109/cvprw.2015.7301306 dblp:conf/cvpr/GeF15 fatcat:r5bjlvt6c5acjgrjbnb7z2glfy

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration [article]

Zi-Ming Wang, Nan Xue, Ling Lei, Gui-Song Xia
2022 arXiv   pre-print
This task is challenging due to the presence of the large number of outliers, the unknown non-rigid deformations and the large sizes of point sets.  ...  In addition, it also incorporates an efficient coherence regularizer for non-rigid transformations to avoid unrealistic deformations.  ...  in the non-overlapped region of the shapes. 2) The number of points consisted in the point sets may be huge. 3) The deformation of point sets is generally unknown and can be non-rigid.  ... 
arXiv:2203.02227v1 fatcat:deiazqyctrc23hrv56lyb23j4a

Non-rigid Point Set Registration with Global-Local Topology Preservation

Song Ge, Guoliang Fan, Meng Ding
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
The first is the previous Coherent Point Drift (CPD) that encodes a global topology constraint by moving one point set coherently to align with the second set.  ...  We propose a new point set registration method, Global-Local Topology Preservation (GLTP), which can cope with complex non-rigid transformations including highly articulated deformation.  ...  Proposed Work Motivation In this work, we study GMM-based non-rigid point set registration, especially, non-rigid articulated registration, where transformations are non-rigid both globally and locally  ... 
doi:10.1109/cvprw.2014.45 dblp:conf/cvpr/GeFD14 fatcat:kmqxisiujfauxabs66dfg4pcly

Articulated Non-Rigid Point Set Registration for Human Pose Estimation from 3D Sensors

Song Ge, Guoliang Fan
2015 Sensors  
First, we integrate two registration techniques that have a complementary nature to cope with non-rigid and articulated deformations of the human body under a variety of poses.  ...  We formulate human pose estimation as a point set registration problem, where we propose three new approaches to address several major technical challenges in this research.  ...  In the first step, we apply the coherent point drift (CPD) algorithm [34] for non-rigid registration between Y and Z.  ... 
doi:10.3390/s150715218 pmid:26131673 pmcid:PMC4541828 fatcat:ekkouwamx5euvetpsiui5y2t2u

Robust Non-Rigid Point Set Registration Using Student's-t Mixture Model

Zhiyong Zhou, Jian Zheng, Yakang Dai, Zhe Zhou, Shi Chen, Jie Tian
2014 PLoS ONE  
Moreover, less registration parameters have to be set manually for our algorithm compared to the popular coherent points drift (CPD) algorithm.  ...  In this paper, we propose a robust non-rigid point set registration algorithm using the Student's-t mixture model.  ...  Myronenko and Song [11] introduced the coherent point drift (CPD) algorithm, which enforces the points to drift coherently by regularizing the deformation field based on the motion coherence theory (  ... 
doi:10.1371/journal.pone.0091381 pmid:24618749 pmcid:PMC3950182 fatcat:glvvgxpm3nccnjieeo2x6zca6q

A refined coherent point drift (CPD) algorithm for point set registration

Peng Wang, Ping Wang, ZhiGuo Qu, YingHui Gao, ZhenKang Shen
2011 Science China Information Sciences  
A refined coherent point drift (CPD) algorithm for point set registration.  ...  The coherent point drift (CPD) algorithm is a powerful approach for point set registration.  ...  , affine, and non-rigid point set registration cases separately, and details of the implementations can be found in [10] .  ... 
doi:10.1007/s11432-011-4465-7 fatcat:cjezrf47cndbfneizhlsuuyviy

Adaptive Non-Rigid Point Set Registration Based on Variational Bayesian

Lijuan Yang, Zheng Tian, Jinhuan Wen, Weidong Yan
2018 Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University  
Robust Point Set Registration Using Gaussian Mixture Models[ J] . IEEE Trans on Pattern Analysis and Ma• [5] Myronenko A, Song X. Point Set RegistrationCoherent Point Drift[ J] .  ...  A New Point Matching Algorithm for NonRigid Registration[ J] .  ... 
doi:10.1051/jnwpu/20183650942 fatcat:4pz4fjzkdzdjnmmt2llejk2doq

3D non-rigid registration using color: Color Coherent Point Drift

Marcelo Saval-Calvo, Jorge Azorin-Lopez, Andres Fuster-Guillo, Victor Villena-Martinez, Robert B. Fisher
2018 Computer Vision and Image Understanding  
In this paper we propose a novel approach to non-rigid registration combining two data spaces in order to robustly calculate the correspondences and transformation between two data sets.  ...  We have propose the Color Coherent Point Drift (CCPD) algorithm (an extension of the CPD method [1]). Evaluation is performed using synthetic and real data.  ...  Coherent Point Drift variants One of the most common algorithms used for non-rigid registration is the Coherent Point Drift (CPD) proposed by Myronenko et al. in [1, 19] .  ... 
doi:10.1016/j.cviu.2018.01.008 fatcat:kb5qbhgslradxm4yd5jnfn6owa

Context-Aware Gaussian Fields for Non-rigid Point Set Registration

Gang Wang, Zhicheng Wang, Yufei Chen, Qiangqiang Zhou, Weidong Zhao
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Point set registration (PSR) is a fundamental problem in computer vision and pattern recognition, and it has been successfully applied to many applications.  ...  CA-LapGF uses a robust objective function and the quasi-Newton algorithm to estimate the likely correspondences, and the non-rigid transformation parameters between two point sets iteratively.  ...  [20] constructed a mixture model, and then proposed an efficient registration algorithm, namely coherence point drift (CPD), where one of the two point sets is modeled as a GMM, the other is the data  ... 
doi:10.1109/cvpr.2016.626 dblp:conf/cvpr/WangWCZZ16 fatcat:ihywpnrcqfg6pidblhcxwmebve
« Previous Showing results 1 — 15 out of 3,381 results