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

02/10/2020
by   Martin Simon, et al.
17

StickyPillars introduces a sparse feature matching method on point clouds. It is the first approach applying Graph Neural Networks on point clouds to stick points of interest. The feature estimation and assignment relies on the optimal transport problem, where the cost is based on the neural network itself. We utilize a Graph Neural Network for context aggregation with the aid of multihead self and cross attention. In contrast to image based feature matching methods, the architecture learns feature extraction in an end-to-end manner. Hence, the approach does not rely on handcrafted features. Our method outperforms state-of-the art matching algorithms, while providing real-time capability.

READ FULL TEXT

page 1

page 3

page 5

page 8

research
11/26/2019

SuperGlue: Learning Feature Matching with Graph Neural Networks

This paper introduces SuperGlue, a neural network that matches two sets ...
research
06/08/2020

Optimal Transport Graph Neural Networks

Current graph neural network (GNN) architectures naively average or sum ...
research
03/05/2023

Robust affine feature matching via quadratic assignment on Grassmannians

GraNNI (Grassmannians for Nearest Neighbours Identification) a new algor...
research
07/22/2020

FLOT: Scene Flow on Point Clouds Guided by Optimal Transport

We propose and study a method called FLOT that estimates scene flow on p...
research
07/30/2021

Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport

Good quality reconstruction and comprehension of a scene rely on 3D esti...
research
11/30/2021

PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images

Most state-of-the-art instance segmentation methods produce binary segme...
research
11/17/2022

Do graph neural networks learn traditional jet substructure?

At the CERN LHC, the task of jet tagging, whose goal is to infer the ori...

Please sign up or login with your details

Forgot password? Click here to reset