# SegMap: 3D Segment Mapping using Data-Driven Descriptors

arXiv: https://arxiv.org/abs/1804.09557 · HTML: https://mlsanity.com/paper/1804.09557/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2018.

## Built on by (most cited first, 21 of 21)

- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM](https://mlsanity.com/paper/2103.05056/) (2021)
- [PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency](https://mlsanity.com/paper/2401.09101/) (2024)
- [NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation](https://mlsanity.com/paper/2103.12292/) (2021)
- [BVMatch: Lidar-based Place Recognition Using Bird's-eye View Images](https://mlsanity.com/paper/2109.00317/) (2021)
- [SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure](https://mlsanity.com/paper/2106.11516/) (2021)
- [Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models](https://mlsanity.com/paper/2409.15451/) (2024)
- [AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition](https://mlsanity.com/paper/2106.09637/) (2021)
- [DARE-SLAM: Degeneracy-Aware and Resilient Loop Closing in Perceptually-Degraded Environments](https://mlsanity.com/paper/2102.05117/) (2021)
- [Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning](https://mlsanity.com/paper/2306.01980/) (2023)
- [Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation](https://mlsanity.com/paper/2302.06149/) (2023)
- [PSE-Match: A Viewpoint-free Place Recognition Method with Parallel Semantic Embedding](https://mlsanity.com/paper/2108.00552/) (2021)
- [ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images](https://mlsanity.com/paper/2503.04475/) (2025)
- [Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps](https://mlsanity.com/paper/2301.08957/) (2023)
- [Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition](https://mlsanity.com/paper/2309.00168/) (2023)
- [LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks](https://mlsanity.com/paper/2501.19382/) (2025)
- [DSC: Deep Scan Context Descriptor for Large-Scale Place Recognition](https://mlsanity.com/paper/2111.13838/) (2021)
- [Descriptellation: Deep Learned Constellation Descriptors](https://mlsanity.com/paper/2203.00567/) (2022)
- [UnLoc: A Universal Localization Method for Autonomous Vehicles using LiDAR, Radar and/or Camera Input](https://mlsanity.com/paper/2307.00741/) (2023)
- [Deep Weakly Supervised Positioning](https://mlsanity.com/paper/2104.04866/) (2021)
- [PNE-SGAN: Probabilistic NDT-Enhanced Semantic Graph Attention Network for LiDAR Loop Closure Detection](https://mlsanity.com/paper/2504.08280/) (2025)

## Abstract (arXiv)

When performing localization and mapping, working at the level of structure can be advantageous in terms of robustness to environmental changes and differences in illumination. This paper presents SegMap: a map representation solution to the localization and mapping problem based on the extraction of segments in 3D point clouds. In addition to facilitating the computationally intensive task of processing 3D point clouds, working at the level of segments addresses the data compression requirements of real-time single- and multi-robot systems. While current methods extract descriptors for the single task of localization, SegMap leverages a data-driven descriptor in order to extract meaningful features that can also be used for reconstructing a dense 3D map of the environment and for extracting semantic information. This is particularly interesting for navigation tasks and for providing visual feedback to end-users such as robot operators, for example in search and rescue scenarios. These capabilities are demonstrated in multiple urban driving and search and rescue experiments. Our method leads to an increase of area under the ROC curve of 28.3% over current state of the art using eigenvalue based features. We also obtain very similar reconstruction capabilities to a model specifically trained for this task. The SegMap implementation will be made available open-source along with easy to run demonstrations at www.github.com/ethz-asl/segmap. A video demonstration is available at https://youtu.be/CMk4w4eRobg.