ArrowPose: Segmentation, Detection, and 5 DoF Pose Estimation Network for Colorless Point Clouds

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

This paper presents a fast detection and 5 DoF (Degrees of Freedom) pose estimation network for colorless point clouds. The pose estimation is calculated from center and top points of the object, predicted by the neural network. The network is trained on synthetic data, and tested on a benchmark dataset, where it demonstrates state-of-the-art performance and outperforms all colorless methods. The network is able to run inference in only 250 milliseconds making it usable in many scenarios. Project page with code at arrowpose.github.io
OriginalsprogEngelsk
Titel2025 IEEE 34th International Symposium on Industrial Electronics (ISIE)
Antal sider6
ForlagIEEE
Publikationsdatojun. 2025
ISBN (Elektronisk)979-8-3503-7479-7
DOI
StatusUdgivet - jun. 2025
Begivenhed34th IEEE International Symposium on Industrial Electronics, ISIE 2025 - Toronto, Canada
Varighed: 20. jun. 202523. jun. 2025

Konference

Konference34th IEEE International Symposium on Industrial Electronics, ISIE 2025
Land/OmrådeCanada
ByToronto
Periode20/06/202523/06/2025
NavnProceedings - IEEE International Symposium on Industrial Electronics (ISIE)
ISSN2163-5137

Fingeraftryk

Dyk ned i forskningsemnerne om 'ArrowPose: Segmentation, Detection, and 5 DoF Pose Estimation Network for Colorless Point Clouds'. Sammen danner de et unikt fingeraftryk.

Citationsformater