Samenvatting

We address the limitations of Deep learning models for 3D
geometry segmentation by using Conditional Random fields (CRF). We
show that CRFs can take advantage of the neighbouring structure of point
clouds to assist the learning of the Deep Learning models (DL). Our hybrid
PN-CRF model is able to learn more optimal weights by taking advantage
of equal-segmentation assignments to neighbouring points. As a result,
it increases the robustness in the model specially for segmentation tasks
where correctly detecting the boundaries between segmentations is very
important.
Originele taal-2English
TitelEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
UitgeverijCiaco
Aantal pagina's6
Volume27
ISBN van geprinte versie978-287-587-065-0
StatusPublished - 24 apr 2019
EvenementEuropean Symposium on Artificial Neural Networks 2019 - Brugge, Belgium
Duur: 24 apr 201926 mrt 2020

Conference

ConferenceEuropean Symposium on Artificial Neural Networks 2019
Verkorte titelESANN
LandBelgium
StadBrugge
Periode24/04/1926/03/20

Vingerafdruk

Duik in de onderzoeksthema's van 'Deep hybrid approach for 3D plane segmentation'. Samen vormen ze een unieke vingerafdruk.

Citeer dit