On Representation of 3D Rotation in the Context of Deep Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pravdová, Viktória, Gajdošech, Lukáš, Ali, Hassan, Kocur, Viktor
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917803659886592
author Pravdová, Viktória
Gajdošech, Lukáš
Ali, Hassan
Kocur, Viktor
author_facet Pravdová, Viktória
Gajdošech, Lukáš
Ali, Hassan
Kocur, Viktor
contents This paper investigates various methods of representing 3D rotations and their impact on the learning process of deep neural networks. We evaluated the performance of ResNet18 networks for 3D rotation estimation using several rotation representations and loss functions on both synthetic and real data. The real datasets contained 3D scans of industrial bins, while the synthetic datasets included views of a simple asymmetric object rendered under different rotations. On synthetic data, we also assessed the effects of different rotation distributions within the training and test sets, as well as the impact of the object's texture. In line with previous research, we found that networks using the continuous 5D and 6D representations performed better than the discontinuous ones.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10350
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Representation of 3D Rotation in the Context of Deep Learning
Pravdová, Viktória
Gajdošech, Lukáš
Ali, Hassan
Kocur, Viktor
Computer Vision and Pattern Recognition
Graphics
65D19
I.4.8; I.3.5
This paper investigates various methods of representing 3D rotations and their impact on the learning process of deep neural networks. We evaluated the performance of ResNet18 networks for 3D rotation estimation using several rotation representations and loss functions on both synthetic and real data. The real datasets contained 3D scans of industrial bins, while the synthetic datasets included views of a simple asymmetric object rendered under different rotations. On synthetic data, we also assessed the effects of different rotation distributions within the training and test sets, as well as the impact of the object's texture. In line with previous research, we found that networks using the continuous 5D and 6D representations performed better than the discontinuous ones.
title On Representation of 3D Rotation in the Context of Deep Learning
topic Computer Vision and Pattern Recognition
Graphics
65D19
I.4.8; I.3.5
url https://arxiv.org/abs/2410.10350