Point Cloud Instance Segmentation with Inaccurate Bounding-Box Annotations

Most existing point cloud instance segmentation methods require accurate and dense point-level annotations, which are extremely laborious to collect. While incomplete and inexact supervision has been exploited to reduce labeling efforts, inaccurate supervision remains under-explored. This kind of su...

Descripción completa

Detalles Bibliográficos
Autores principales: Peng, Yinyin, Feng, Hui, Chen, Tao, Hu, Bo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9960887/
https://www.ncbi.nlm.nih.gov/pubmed/36850943
http://dx.doi.org/10.3390/s23042343

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9960887/
https://www.ncbi.nlm.nih.gov/pubmed/36850943
http://dx.doi.org/10.3390/s23042343

Ejemplares similares