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.
Denis, L, Royen, RD & Munteanu, A 2023, Improved Block Merging for 3D Point Cloud Instance Segmentation. in 2023 24th International Conference on Digital Signal Processing (DSP). Proceedings - International Conference on Digital Signal Processing (DSP), IEEE, pp. 1-5, 24th International Conference on Digital Signal Processing, Island of Rhodes, Greece, 11/06/23. https://doi.org/10.1109/DSP58604.2023.10167976
Denis, L., Royen, R. D., & Munteanu, A. (2023). Improved Block Merging for 3D Point Cloud Instance Segmentation. In 2023 24th International Conference on Digital Signal Processing (DSP) (pp. 1-5). (Proceedings - International Conference on Digital Signal Processing (DSP)). IEEE. https://doi.org/10.1109/DSP58604.2023.10167976
@inproceedings{e5b6739a7e564dc3902b5c1d47f6e2db,
title = "Improved Block Merging for 3D Point Cloud Instance Segmentation",
abstract = "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.",
author = "Leon Denis and Royen, {Remco Donovan} and Adrian Munteanu",
note = "Funding Information: The second author is funded by Fonds Wetenschappelijk Onderzoek (FWO) - 1S89420N Publisher Copyright: {\textcopyright} 2023 IEEE.; 24th International Conference on Digital Signal Processing, 24th DSP 2023 ; Conference date: 11-06-2023 Through 13-06-2023",
year = "2023",
month = jun,
day = "11",
doi = "10.1109/DSP58604.2023.10167976",
language = "English",
isbn = "979-8-3503-3960-4",
series = "Proceedings - International Conference on Digital Signal Processing (DSP)",
publisher = "IEEE",
pages = "1--5",
booktitle = "2023 24th International Conference on Digital Signal Processing (DSP)",
url = "https://2023.ic-dsp.org/",
}