# LTS-NET: End-to-end Unsupervised Learning of Long-Term 3D Stable objects

arXiv: https://arxiv.org/abs/2301.03426 · HTML: https://mlsanity.com/paper/2301.03426/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 9 Jan 2023.

## Builds on (most cited first, 11 of 11)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [FAST-LIO2: Fast Direct LiDAR-inertial Odometry](https://mlsanity.com/paper/2107.06829/) (2021)
- [Identifying Unknown Instances for Autonomous Driving](https://mlsanity.com/paper/1910.11296/) (2019)
- [Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform](https://mlsanity.com/paper/2008.09162/) (2020)
- [ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building](https://mlsanity.com/paper/2103.04316/) (2021)
- [Long-Term Urban Vehicle Localization Using Pole Landmarks Extracted from 3-D Lidar Scans](https://mlsanity.com/paper/1910.10550/) (2019)
- [Unsupervised Learning of 3D Scene Flow from Monocular Camera](https://mlsanity.com/paper/2206.03673/) (2022)
- [Deep Semantic Classification for 3D LiDAR Data](https://mlsanity.com/paper/1706.08355/) (2017)
- [Self-Improving Semantic Perception for Indoor Localisation](https://mlsanity.com/paper/2105.01595/) (2021)

## Built on by (most cited first, 1 of 1)

- [Chamelion: Reliable Change Detection for Long-Term LiDAR Mapping in Transient Environments](https://mlsanity.com/paper/2602.08189/) (2026)

## Abstract (arXiv)

In this research, we present an end-to-end data-driven pipeline for determining the long-term stability status of objects within a given environment, specifically distinguishing between static and dynamic objects. Understanding object stability is key for mobile robots since long-term stable objects can be exploited as landmarks for long-term localisation. Our pipeline includes a labelling method that utilizes historical data from the environment to generate training data for a neural network. Rather than utilizing discrete labels, we propose the use of point-wise continuous label values, indicating the spatio-temporal stability of individual points, to train a point cloud regression network named LTS-NET. Our approach is evaluated on point cloud data from two parking lots in the NCLT dataset, and the results show that our proposed solution, outperforms direct training of a classification model for static vs dynamic object classification.