Smooth Deformation Field-based Mismatch Removal in Real-time
- URL: http://arxiv.org/abs/2007.08553v1
- Date: Thu, 16 Jul 2020 18:20:25 GMT
- Title: Smooth Deformation Field-based Mismatch Removal in Real-time
- Authors: Haoyin Zhou, Jagadeesan Jayender
- Abstract summary: Non-rigid deformation makes it difficult to remove mismatches because no parametric transformation can be found.
We propose an algorithm based on the re-weighting and 1-point RANSAC strategy (R1P-RNSC)
We show that the combination of the two algorithms has the best accuracy compared to other state-of-the-art methods.
- Score: 10.181846237133167
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper studies the mismatch removal problem, which may serve as the
subsequent step of feature matching. Non-rigid deformation makes it difficult
to remove mismatches because no parametric transformation can be found. To
solve this problem, we first propose an algorithm based on the re-weighting and
1-point RANSAC strategy (R1P-RNSC), which is a parametric method under a
reasonable assumption that the non-rigid deformation can be approximately
represented by multiple locally rigid transformations. R1P-RNSC is fast but
suffers from a drawback that the local smoothing information cannot be taken
into account. Then, we propose a non-parametric algorithm based on the
expectation maximization algorithm and dual quaternion (EMDQ) representation to
generate the smooth deformation field. The two algorithms compensate for the
drawbacks of each other. Specifically, EMDQ needs good initial values provided
by R1P-RNSC, and R1P-RNSC needs EMDQ for refinement. Experimental results with
real-world data demonstrate that the combination of the two algorithms has the
best accuracy compared to other state-of-the-art methods, which can handle up
to 85% of outliers in real-time. The ability to generate dense deformation
field from sparse matches with outliers in real-time makes the proposed
algorithms have many potential applications, such as non-rigid registration and
SLAM.
Related papers
- Worth Their Weight: Randomized and Regularized Block Kaczmarz Algorithms without Preprocessing [2.542838926315103]
We analyze the convergence of the randomized block Kaczmarz method (RBK) when the data is sampled uniformly, showing that its iterates converge in a Monte Carlo sense to a $textit$ least-squares solution.
We resolve these issues by incorporating regularization into the RBK.
Numerical experiments, including examples arising from natural gradient optimization, suggest that the regularized algorithm, ReBlocK, outperforms minibatch gradient descent for realistic problems that exhibit fast singular value decay.
arXiv Detail & Related papers (2025-02-02T19:23:46Z) - Variable Substitution and Bilinear Programming for Aligning Partially Overlapping Point Sets [48.1015832267945]
This research presents a method to meet requirements through the minimization objective function of the RPM algorithm.
A branch-and-bound (BnB) algorithm is devised, which solely branches over the parameters, thereby boosting convergence rate.
Empirical evaluations demonstrate better robustness of the proposed methodology against non-rigid deformation, positional noise, and outliers, when compared with prevailing state-of-the-art transformations.
arXiv Detail & Related papers (2024-05-14T13:28:57Z) - Stochastic Optimization for Non-convex Problem with Inexact Hessian
Matrix, Gradient, and Function [99.31457740916815]
Trust-region (TR) and adaptive regularization using cubics have proven to have some very appealing theoretical properties.
We show that TR and ARC methods can simultaneously provide inexact computations of the Hessian, gradient, and function values.
arXiv Detail & Related papers (2023-10-18T10:29:58Z) - Fast and Robust Non-Rigid Registration Using Accelerated
Majorization-Minimization [35.66014845211251]
Non-rigid registration, which deforms a source shape in a non-rigid way to align with a target shape, is a classical problem in computer vision.
Existing methods typically adopt the $ell_p$ type robust norm to measure the alignment error and regularize the smoothness of deformation.
We propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization.
arXiv Detail & Related papers (2022-06-07T16:00:33Z) - Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth
Nonlinear TD Learning [145.54544979467872]
We propose two single-timescale single-loop algorithms that require only one data point each step.
Our results are expressed in a form of simultaneous primal and dual side convergence.
arXiv Detail & Related papers (2020-08-23T20:36:49Z) - Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
Local features provide region-to-region rather than point-to-point correspondences.
We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline.
Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
arXiv Detail & Related papers (2020-07-20T12:07:48Z) - Accelerated Message Passing for Entropy-Regularized MAP Inference [89.15658822319928]
Maximum a posteriori (MAP) inference in discrete-valued random fields is a fundamental problem in machine learning.
Due to the difficulty of this problem, linear programming (LP) relaxations are commonly used to derive specialized message passing algorithms.
We present randomized methods for accelerating these algorithms by leveraging techniques that underlie classical accelerated gradient.
arXiv Detail & Related papers (2020-07-01T18:43:32Z) - Quasi-Newton Solver for Robust Non-Rigid Registration [35.66014845211251]
We propose a formulation for robust non-rigid registration based on a globally smooth robust estimator for data fitting and regularization.
We apply the majorization-minimization algorithm to the problem, which reduces each iteration to solving a simple least-squares problem with L-BFGS.
arXiv Detail & Related papers (2020-04-09T01:45:05Z) - Second-Order Guarantees in Centralized, Federated and Decentralized
Nonconvex Optimization [64.26238893241322]
Simple algorithms have been shown to lead to good empirical results in many contexts.
Several works have pursued rigorous analytical justification for studying non optimization problems.
A key insight in these analyses is that perturbations play a critical role in allowing local descent algorithms.
arXiv Detail & Related papers (2020-03-31T16:54:22Z) - Semi-analytic approximate stability selection for correlated data in
generalized linear models [3.42658286826597]
We propose a novel approximate inference algorithm that can conduct Stability Selection without the repeated fitting.
The algorithm is based on the replica method of statistical mechanics and vector approximate message passing of information theory.
Numerical experiments indicate that the algorithm exhibits fast convergence and high approximation accuracy for both synthetic and real-world data.
arXiv Detail & Related papers (2020-03-19T10:43:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.