# LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks

arXiv: https://arxiv.org/abs/2501.19382 · HTML: https://mlsanity.com/paper/2501.19382/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 31 Jan 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [MinkLoc3D: Point Cloud Based Large-Scale Place Recognition](https://mlsanity.com/paper/2011.04530/) (2020)
- [SuMa++: Efficient LiDAR-based Semantic SLAM](https://mlsanity.com/paper/2105.11320/) (2021)
- [SimGNN: A Neural Network Approach to Fast Graph Similarity Computation](https://mlsanity.com/paper/1808.05689/) (2018)
- [Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments](https://mlsanity.com/paper/2109.13494/) (2021)
- [OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition](https://mlsanity.com/paper/2203.03397/) (2022)
- [LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM](https://mlsanity.com/paper/2103.05056/) (2021)
- [SegMatch: Segment based loop-closure for 3D point clouds](https://mlsanity.com/paper/1609.07720/) (2016)
- [F-LOAM: Fast LiDAR Odometry And Mapping](https://mlsanity.com/paper/2107.00822/) (2021)
- [Semantic Graph Based Place Recognition for 3D Point Clouds](https://mlsanity.com/paper/2008.11459/) (2020)
- [Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection](https://mlsanity.com/paper/2003.05656/) (2020)
- [SSC: Semantic Scan Context for Large-Scale Place Recognition](https://mlsanity.com/paper/2107.00382/) (2021)
- [SegMap: 3D Segment Mapping using Data-Driven Descriptors](https://mlsanity.com/paper/1804.09557/) (2018)
- [Measuring robustness of Visual SLAM](https://mlsanity.com/paper/1910.04755/) (2019)
- [SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure](https://mlsanity.com/paper/2106.11516/) (2021)

## Built on by (most cited first, 2 of 2)

- [Advanced techniques and applications of LiDAR Place Recognition in Agricultural Environments: A Comprehensive Survey](https://mlsanity.com/paper/2601.22198/) (2026)
- [PNE-SGAN: Probabilistic NDT-Enhanced Semantic Graph Attention Network for LiDAR Loop Closure Detection](https://mlsanity.com/paper/2504.08280/) (2025)

## Abstract (arXiv)

In this paper, we propose a novel loop closure detection algorithm that uses graph attention neural networks to encode semantic graphs to perform place recognition and then use semantic registration to estimate the 6 DoF relative pose constraint. Our place recognition algorithm has two key modules, namely, a semantic graph encoder module and a graph comparison module. The semantic graph encoder employs graph attention networks to efficiently encode spatial, semantic and geometric information from the semantic graph of the input point cloud. We then use self-attention mechanism in both node-embedding and graph-embedding steps to create distinctive graph vectors. The graph vectors of the current scan and a keyframe scan are then compared in the graph comparison module to identify a possible loop closure. Specifically, employing the difference of the two graph vectors showed a significant improvement in performance, as shown in ablation studies. Lastly, we implemented a semantic registration algorithm that takes in loop closure candidate scans and estimates the relative 6 DoF pose constraint for the LiDAR SLAM system. Extensive evaluation on public datasets shows that our model is more accurate and robust, achieving 13% improvement in maximum F1 score on the SemanticKITTI dataset, when compared to the baseline semantic graph algorithm. For the benefit of the community, we open-source the complete implementation of our proposed algorithm and custom implementation of semantic registration at https://github.com/crepuscularlight/SemanticLoopClosure