GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

Rigid registration of point clouds is a fundamental problem in computer vision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, conventional methods like ICP and its many variants can provide adequate solutions. In absence of a suitable initialization and in the presence of a high outlier rate or in the case of small overlap though the task of rigid registration still presents great challenges. The advent of deep learning in computer vision has brought new drive to research on this topic, since it provides the possibility to learn expressive feature-representations and provide one-shot estimates instead of depending on time-consuming iterations of conventional robust methods. Yet, the rotation and permutation invariant nature of point clouds poses its own challenges to deep learning, resulting in loss of performance and low generalization capability due to sensitivity to outliers and characteristics of 3D scans not present during network training. In this work, we present a novel fast and light-weight network architecture using the attention mechanism to augment point descriptors at inference time to optimally suit the registration task of the specific point clouds it is presented with. Employing a fully-connected graph both within and between point clouds lets the network reason about the importance and reliability of points for registration, making our approach robust to outliers, low overlap and unseen data. We test the performance of our registration algorithm on different registration and generalization tasks and provide information on runtime and resource consumption. The code and trained weights are available at https://github.com/mordecaimalignatius/GAFAR/.
Originalspracheenglisch
TitelProceedings of the 2023 European Conference on Mobile Robots (ECMR)
DOIs
PublikationsstatusVeröffentlicht - 2023
Veranstaltung11th European Conference on Mobile Robots: ECMR 2023 - University of Coimbra, Coimbra, Portugal
Dauer: 4 Sept. 20237 Sept. 2023

Konferenz

Konferenz11th European Conference on Mobile Robots
KurztitelECMR2023
Land/GebietPortugal
OrtCoimbra
Zeitraum4/09/237/09/23

Fingerprint

Untersuchen Sie die Forschungsthemen von „GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren