AI Chat AI Image Generator AI Video Text to Speech

Robust affine feature matching via quadratic assignment on Grassmannians

03/05/2023

∙

by Alexander Kolpakov, et al.

∙

∙

GraNNI (Grassmannians for Nearest Neighbours Identification) a new algorithm to solve the problem of affine registration is proposed. The algorithm is based on the Grassmannian of k–dimensional planes in ℝ^n and minimizing the Frobenius norm between the two elements of the Grassmannian. The Quadratic Assignment Problem (QAP) is used to find the matching. The results of the experiments show that the algorithm is more robust to noise and point discrepancy in point clouds than previous approaches.

Alexander Kolpakov
4 publications
Michael Werman
22 publications

page 7

page 12

page 13

research

∙ 02/10/2020

StickyPillars: Robust feature matching on point clouds using Graph Neural Networks

StickyPillars introduces a sparse feature matching method on point cloud...

17 Martin Simon, et al. ∙

research

∙ 10/23/2019

Iterative Matching Point

In this paper, we propose a neural network-based point cloud registratio...

0 Jiahao Li, et al. ∙

research

∙ 11/23/2021

GenReg: Deep Generative Method for Fast Point Cloud Registration

Accurate and efficient point cloud registration is a challenge because t...

0 Xiaoshui Huang, et al. ∙

research

∙ 03/19/2020

Efficient and Robust Shape Correspondence via Sparsity-Enforced Quadratic Assignment

In this work, we introduce a novel local pairwise descriptor and then de...

0 Rui Xiang, et al. ∙

research

∙ 10/05/2020

Best Buddies Registration for Point Clouds

We propose new, and robust, loss functions for the point cloud registrat...

0 Amnon Drory, et al. ∙

research

∙ 11/04/2020

Affine invariant triangulations

We study affine invariant 2D triangulation methods. That is, methods tha...

0 Prosenjit Bose, et al. ∙

research

∙ 12/10/2022

An approach to robust ICP initialization

In this note, we propose an approach to initialize the Iterative Closest...

0 Alexander Kolpakov, et al. ∙