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

TL;DR

This paper introduces a novel method for point cloud registration that combines implicit distance fields with a pseudo third point set, achieving high accuracy and speed without the need for training, suitable for incremental 3D reconstruction.

Contribution

It presents a non-Deep Learning registration algorithm using implicit distance fields that rivals deep learning methods in accuracy and speed without requiring training.

Findings

More accurate than conventional models

Achieves competitive performance without training

Faster than deep learning-based registration methods

Abstract

In recent years, implicit functions have drawn attention in the field of 3D reconstruction and have successfully been applied with Deep Learning. However, for incremental reconstruction, implicit function-based registrations have been rarely explored. Inspired by the high precision of deep learning global feature registration, we propose to combine this with distance fields. We generalize the algorithm to a non-Deep Learning setting while retaining the accuracy. Our algorithm is more accurate than conventional models while, without any training, it achieves a competitive performance and faster speed, compared to Deep Learning-based registration models. The implementation is available on github for the research community.