PointNet with Spin Images
The result's identifiers
Result code in 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>
Result on the web
<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
—
Alternative languages
Result language
angličtina
Original language name
PointNet with Spin Images
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
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
—
Number of pages
12
Pages from-to
85-96
Publisher name
CEUR Workshop Proceedings (CEUR-WS.org)
Place of publication
RWTH Aachen University
Event location
Limassol, Cyprus
Event date
Jan 20, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—