Saved in:
Bibliographic Details
Main Authors: Talwar, Abhimanyu, Laasri, Julien
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.14583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915295186124800
author Talwar, Abhimanyu
Laasri, Julien
author_facet Talwar, Abhimanyu
Laasri, Julien
contents Recently proposed neural network architectures like PointNet [QSMG16] and PointNet++ [QYSG17] have made it possible to apply Deep Learning to 3D point sets. The feature representations of shapes learned by these two networks enabled training classifiers for Semantic Segmentation, and more recently for Instance Segmentation via the Similarity Group Proposal Network (SGPN) [WYHN17]. One area of improvement which has been highlighted by SGPN's authors, pertains to use of memory intensive similarity matrices which occupy memory quadratic in the number of points. In this report, we attempt to tackle this issue through use of two sampling based methods, which compute Instance Segmentation on a sub-sampled Point Set, and then extrapolate labels to the complete set using the nearest neigbhour approach. While both approaches perform equally well on large sub-samples, the random-based strategy gives the most improvements in terms of speed and memory usage.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14583
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Instance Segmentation for Point Sets
Talwar, Abhimanyu
Laasri, Julien
Computer Vision and Pattern Recognition
Machine Learning
68T45
I.2.10
Recently proposed neural network architectures like PointNet [QSMG16] and PointNet++ [QYSG17] have made it possible to apply Deep Learning to 3D point sets. The feature representations of shapes learned by these two networks enabled training classifiers for Semantic Segmentation, and more recently for Instance Segmentation via the Similarity Group Proposal Network (SGPN) [WYHN17]. One area of improvement which has been highlighted by SGPN's authors, pertains to use of memory intensive similarity matrices which occupy memory quadratic in the number of points. In this report, we attempt to tackle this issue through use of two sampling based methods, which compute Instance Segmentation on a sub-sampled Point Set, and then extrapolate labels to the complete set using the nearest neigbhour approach. While both approaches perform equally well on large sub-samples, the random-based strategy gives the most improvements in terms of speed and memory usage.
title Instance Segmentation for Point Sets
topic Computer Vision and Pattern Recognition
Machine Learning
68T45
I.2.10
url https://arxiv.org/abs/2505.14583