PointNet with Spin Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10425001" target="_blank" >RIV/00216208:11320/20:10425001 - isvavai.cz</a>

Výsledek na webu

<a href="http://ceur-ws.org/Vol-2568/paper8.pdf" target="_blank" >http://ceur-ws.org/Vol-2568/paper8.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

PointNet with Spin Images

Popis výsledku v původním jazyce

Machine learning on 3D point clouds is challenging due to the absence of natural ordering of the points. PointNet is a neural network architecture capable of processing such unordered point sets directly, which has achieved promising results on classification and segmentation tasks. We explore methods of utilizing point neighborhood features within PointNet and their impact on classification performance. We propose neural models that operate on point clouds accompanied by point features. The results of our experiments suggest that traditional spin image representations of point neighborhoods can improve classification effectiveness of PointNet on datasets comprised of objects that are not aligned into canonical orientation. Furthermore, we introduce a feature-based alternative to spatial transformer, which is a sub-network of PointNet responsible for aligning misaligned objects into canonical orientation. Additional experiments demonstrate that the alternative might be competitive with spatial transformer on challenging datasets.

Název v anglickém jazyce

PointNet with Spin Images

Popis výsledku anglicky

Machine learning on 3D point clouds is challenging due to the absence of natural ordering of the points. PointNet is a neural network architecture capable of processing such unordered point sets directly, which has achieved promising results on classification and segmentation tasks. We explore methods of utilizing point neighborhood features within PointNet and their impact on classification performance. We propose neural models that operate on point clouds accompanied by point features. The results of our experiments suggest that traditional spin image representations of point neighborhoods can improve classification effectiveness of PointNet on datasets comprised of objects that are not aligned into canonical orientation. Furthermore, we introduce a feature-based alternative to spatial transformer, which is a sub-network of PointNet responsible for aligning misaligned objects into canonical orientation. Additional experiments demonstrate that the alternative might be competitive with spatial transformer on challenging datasets.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the SOFSEM 2020 Doctoral Student Research Forum co-located with the 46th International Conference on Current Trends in Theory and Practice of Computer Science (SOFSEM 2020), Limassol, Cyprus, January 20-24, 2020

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

12

Strana od-do

85-96

Název nakladatele

CEUR Workshop Proceedings (CEUR-WS.org)

Místo vydání

RWTH Aachen University

Místo konání akce

Limassol, Cyprus

Datum konání akce

20. 1. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—