Fine-grained Metrics for Point Cloud Semantic Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Zhuheng, Wu, Ting, Dai, Yuewei, Li, Weiqing, Su, Zhiyong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916341155364864
author Lu, Zhuheng
Wu, Ting
Dai, Yuewei
Li, Weiqing
Su, Zhiyong
author_facet Lu, Zhuheng
Wu, Ting
Dai, Yuewei
Li, Weiqing
Su, Zhiyong
contents Two forms of imbalances are commonly observed in point cloud semantic segmentation datasets: (1) category imbalances, where certain objects are more prevalent than others; and (2) size imbalances, where certain objects occupy more points than others. Because of this, the majority of categories and large objects are favored in the existing evaluation metrics. This paper suggests fine-grained mIoU and mAcc for a more thorough assessment of point cloud segmentation algorithms in order to address these issues. Richer statistical information is provided for models and datasets by these fine-grained metrics, which also lessen the bias of current semantic segmentation metrics towards large objects. The proposed metrics are used to train and assess various semantic segmentation algorithms on three distinct indoor and outdoor semantic segmentation datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2407_21289
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-grained Metrics for Point Cloud Semantic Segmentation
Lu, Zhuheng
Wu, Ting
Dai, Yuewei
Li, Weiqing
Su, Zhiyong
Computer Vision and Pattern Recognition
Graphics
Two forms of imbalances are commonly observed in point cloud semantic segmentation datasets: (1) category imbalances, where certain objects are more prevalent than others; and (2) size imbalances, where certain objects occupy more points than others. Because of this, the majority of categories and large objects are favored in the existing evaluation metrics. This paper suggests fine-grained mIoU and mAcc for a more thorough assessment of point cloud segmentation algorithms in order to address these issues. Richer statistical information is provided for models and datasets by these fine-grained metrics, which also lessen the bias of current semantic segmentation metrics towards large objects. The proposed metrics are used to train and assess various semantic segmentation algorithms on three distinct indoor and outdoor semantic segmentation datasets.
title Fine-grained Metrics for Point Cloud Semantic Segmentation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2407.21289