Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration

11/29/2022
by   David Bojanić, et al.
0

Learning universal representations across different applications domain is an open research problem. In fact, finding universal architecture within the same application but across different types of datasets is still unsolved problem too, especially in applications involving processing 3D point clouds. In this work we experimentally test several state-of-the-art learning-based methods for 3D point cloud registration against the proposed non-learning baseline registration method. The proposed method either outperforms or achieves comparable results w.r.t. learning based methods. In addition, we propose a dataset on which learning based methods have a hard time to generalize. Our proposed method and dataset, along with the provided experiments, can be used in further research in studying effective solutions for universal representations. Our source code is available at: github.com/DavidBoja/greedy-grid-search.

READ FULL TEXT

page 1

page 4

research
12/29/2019

Target-less registration of point clouds: A review

Point cloud registration has been one of the basic steps of point cloud ...
research
08/24/2017

Learning a 3D descriptor for cross-source point cloud registration from synthetic data

As the development of 3D sensors, registration of 3D data (e.g. point cl...
research
05/23/2022

RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds

3D motion estimation including scene flow and point cloud registration h...
research
05/31/2022

Indirect Point Cloud Registration: Aligning Distance Fields using a Pseudo Third Point Ses

In recent years, implicit functions have drawn attention in the field of...
research
09/01/2022

PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration

Multi-instance point cloud registration is the problem of estimating mul...
research
04/25/2023

BO-ICP: Initialization of Iterative Closest Point Based on Bayesian Optimization

Typical algorithms for point cloud registration such as Iterative Closes...
research
03/02/2022

A Simple and Universal Rotation Equivariant Point-cloud Network

Equivariance to permutations and rigid motions is an important inductive...

Please sign up or login with your details

Forgot password? Click here to reset