Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Norwegian Open Resea...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 1 versions
addClaim

Deep Learning on 3D Feature Descriptors

Authors: Puente, Philip Øygarden;

Deep Learning on 3D Feature Descriptors

Abstract

I de siste årene har 3D-figur data blitt lettere å få tak i, delvis grunnet kommersielle sensorer og utbredt bruk av 3D-printere. Det er derfor ønskelig å ta i bruk dyp-læringsmetoder, som har vist seg å være anvendbare for mange ulike formål, og tilpasse de til 3D data. Den uregelmessige størrelsen på 3D data gjør det dessverre vanskelig å overføre disse teknikkene direkte. Kanskje er det mulig å ta i bruk 3D egenskapsbeskrivelser som et omformingssteg for å regularisere dataen? Eksperimenter der Siamesiske nevrale nettverk ble trent opp på Spin Images, Viewpoint Feature Histogram og Fast Point Feature Histogram, viser at det ikke bare er mulig, men det gir mer presise resultater sammenlignet med en mer primitiv punktsky trimmingsmetode. Ikke nok er det, men 3D egenskapsbekrivelser kan også hjelpe til å redusere størrelsen på nevrale nettverk, uten å ofre nøyaktighet. Dette bidrar til å gjøre det raskere for nettverkene å trenes opp og å gjøre prognoser.

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green