P3-SAM: Native 3D Part Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ma, Changfeng, Li, Yang, Yan, Xinhao, Xu, Jiachen, Yang, Yunhan, Wang, Chunshi, Zhao, Zibo, Guo, Yanwen, Chen, Zhuo, Guo, Chunchao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908557888192512
author Ma, Changfeng
Li, Yang
Yan, Xinhao
Xu, Jiachen
Yang, Yunhan
Wang, Chunshi
Zhao, Zibo
Guo, Yanwen
Chen, Zhuo
Guo, Chunchao
author_facet Ma, Changfeng
Li, Yang
Yan, Xinhao
Xu, Jiachen
Yang, Yunhan
Wang, Chunshi
Zhao, Zibo
Guo, Yanwen
Chen, Zhuo
Guo, Chunchao
contents Segmenting 3D assets into their constituent parts is crucial for enhancing 3D understanding, facilitating model reuse, and supporting various applications such as part generation. However, current methods face limitations such as poor robustness when dealing with complex objects and cannot fully automate the process. In this paper, we propose a native 3D point-promptable part segmentation model termed P$^3$-SAM, designed to fully automate the segmentation of any 3D objects into components. Inspired by SAM, P$^3$-SAM consists of a feature extractor, multiple segmentation heads, and an IoU predictor, enabling interactive segmentation for users. We also propose an algorithm to automatically select and merge masks predicted by our model for part instance segmentation. Our model is trained on a newly built dataset containing nearly 3.7 million models with reasonable segmentation labels. Comparisons show that our method achieves precise segmentation results and strong robustness on any complex objects, attaining state-of-the-art performance. Our project page is available at https://murcherful.github.io/P3-SAM/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06784
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle P3-SAM: Native 3D Part Segmentation
Ma, Changfeng
Li, Yang
Yan, Xinhao
Xu, Jiachen
Yang, Yunhan
Wang, Chunshi
Zhao, Zibo
Guo, Yanwen
Chen, Zhuo
Guo, Chunchao
Computer Vision and Pattern Recognition
Segmenting 3D assets into their constituent parts is crucial for enhancing 3D understanding, facilitating model reuse, and supporting various applications such as part generation. However, current methods face limitations such as poor robustness when dealing with complex objects and cannot fully automate the process. In this paper, we propose a native 3D point-promptable part segmentation model termed P$^3$-SAM, designed to fully automate the segmentation of any 3D objects into components. Inspired by SAM, P$^3$-SAM consists of a feature extractor, multiple segmentation heads, and an IoU predictor, enabling interactive segmentation for users. We also propose an algorithm to automatically select and merge masks predicted by our model for part instance segmentation. Our model is trained on a newly built dataset containing nearly 3.7 million models with reasonable segmentation labels. Comparisons show that our method achieves precise segmentation results and strong robustness on any complex objects, attaining state-of-the-art performance. Our project page is available at https://murcherful.github.io/P3-SAM/.
title P3-SAM: Native 3D Part Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06784