Improved Block Merging for 3D Point Cloud Instance Segmentation

Onderzoeksoutput: Conference paper

Samenvatting

This paper proposes a novel block merging algorithm suitable for any block-based 3D instance segmentation technique. The proposed work improves over the state-of-the-art by allowing wrongly labelled points of already processed blocks to be corrected through label propagation. By doing so, instance overlap between blocks is not anymore necessary to produce the desirable results, which is the main limitation of the current art. Our experiments show that the proposed block merging algorithm significantly and consistently improves the obtained accuracy for all evaluation metrics employed in literature, regardless of the underlying network architecture.
Originele taal-2English
Titel2023 24th International Conference on Digital Signal Processing (DSP)
UitgeverijIEEE
Pagina's1-5
Aantal pagina's5
ISBN van elektronische versie979-8-3503-3959-8
ISBN van geprinte versie979-8-3503-3960-4
DOI's
StatusPublished - 11 jun 2023
Evenement24th International Conference on Digital Signal Processing - Island of Rhodes · Greece, Island of Rhodes, Greece
Duur: 11 jun 202313 jun 2023
https://2023.ic-dsp.org/

Publicatie series

NaamProceedings - International Conference on Digital Signal Processing (DSP)
UitgeverijIEEE
ISSN van geprinte versie1546-1874
ISSN van elektronische versie2165-3577

Conference

Conference24th International Conference on Digital Signal Processing
Verkorte titel24th DSP 2023
Land/RegioGreece
StadIsland of Rhodes
Periode11/06/2313/06/23
Internet adres

Bibliografische nota

Funding Information:
The second author is funded by Fonds Wetenschappelijk
Onderzoek (FWO) - 1S89420N

Publisher Copyright:
© 2023 IEEE.

Vingerafdruk

Duik in de onderzoeksthema's van 'Improved Block Merging for 3D Point Cloud Instance Segmentation'. Samen vormen ze een unieke vingerafdruk.

Citeer dit