# SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention

arXiv: https://arxiv.org/abs/2308.03718 · HTML: https://mlsanity.com/paper/2308.03718/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration](https://mlsanity.com/paper/1905.04153/) (2019)
- [USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds](https://mlsanity.com/paper/1904.00229/) (2019)
- [PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval](https://mlsanity.com/paper/1904.09793/) (2019)
- [Fast and Robust Iterative Closest Point](https://mlsanity.com/paper/2007.07627/) (2020)
- [SegMatch: Segment based loop-closure for 3D point clouds](https://mlsanity.com/paper/1609.07720/) (2016)
- [Semantic Graph Based Place Recognition for 3D Point Clouds](https://mlsanity.com/paper/2008.11459/) (2020)
- [PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds](https://mlsanity.com/paper/2110.01269/) (2021)
- [SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure](https://mlsanity.com/paper/2106.11516/) (2021)
- [BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR](https://mlsanity.com/paper/2206.15154/) (2022)
- [Graph Structure from Point Clouds: Geometric Attention is All You Need](https://mlsanity.com/paper/2307.16662/) (2023)

## Built on by (most cited first, 5 of 5)

- [Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models](https://mlsanity.com/paper/2308.04220/) (2023)
- [That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation](https://mlsanity.com/paper/2403.04755/) (2024)
- [NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms](https://mlsanity.com/paper/2410.11031/) (2024)
- [Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graph](https://mlsanity.com/paper/2408.15750/) (2024)
- [Introspection in Learned Semantic Scene Graph Localisation](https://mlsanity.com/paper/2510.07053/) (2025)

## Abstract (arXiv)

This paper proposes a Graph Neural Network(GNN)-based method for exploiting semantics and local geometry to guide the identification of reliable pointcloud registration candidates. Semantic and morphological features of the environment serve as key reference points for registration, enabling accurate lidar-based pose estimation. Our novel lightweight static graph structure informs our attention-based node aggregation network by identifying semantic-instance relationships, acting as an inductive bias to significantly reduce the computational burden of pointcloud registration. By connecting candidate nodes and exploiting cross-graph attention, we identify confidence scores for all potential registration correspondences and estimate the displacement between pointcloud scans. Our pipeline enables introspective analysis of the model's performance by correlating it with the individual contributions of local structures in the environment, providing valuable insights into the system's behaviour. We test our method on the KITTI odometry dataset, achieving competitive accuracy compared to benchmark methods and a higher track smoothness while relying on significantly fewer network parameters.