# Instance Segmentation for Point Sets

Source: [Instance Segmentation for Point Sets](<https://www.sota2.com/research/paper/68fa78a31e209131cea797f7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:43:14.257Z

Authors: Abhimanyu Talwar, Julien Laasri

Published: 2025-05-20T16:40:01.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.14583>)

[PDF](<https://arxiv.org/pdf/2505.14583.pdf>)