# NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation

arXiv: https://arxiv.org/abs/2103.12292 · HTML: https://mlsanity.com/paper/2103.12292/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 23 Mar 2021.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (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)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [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)
- [PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization](https://mlsanity.com/paper/2003.02392/) (2020)
- [SegMap: 3D Segment Mapping using Data-Driven Descriptors](https://mlsanity.com/paper/1804.09557/) (2018)
- [Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU](https://mlsanity.com/paper/1902.10194/) (2019)
- [Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments](https://mlsanity.com/paper/2003.01875/) (2020)

## Built on by (most cited first, 30 of 38)

- [Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training](https://mlsanity.com/paper/2203.00972/) (2022)
- [BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images](https://mlsanity.com/paper/2302.14325/) (2023)
- [Text2Loc: 3D Point Cloud Localization from Natural Language](https://mlsanity.com/paper/2311.15977/) (2023)
- [TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields](https://mlsanity.com/paper/2105.11605/) (2021)
- [InCloud: Incremental Learning for Point Cloud Place Recognition](https://mlsanity.com/paper/2203.00807/) (2022)
- [CASSPR: Cross Attention Single Scan Place Recognition](https://mlsanity.com/paper/2211.12542/) (2022)
- [SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data](https://mlsanity.com/paper/2209.07951/) (2022)
- [CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data](https://mlsanity.com/paper/2302.01665/) (2023)
- [Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM](https://mlsanity.com/paper/2309.08086/) (2023)
- [MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity](https://mlsanity.com/paper/2112.06539/) (2021)
- [HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud](https://mlsanity.com/paper/2204.05481/) (2022)
- [CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework](https://mlsanity.com/paper/2503.02593/) (2025)
- [SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition](https://mlsanity.com/paper/2407.08260/) (2024)
- [MSSPlace: Multi-Sensor Place Recognition with Visual and Text Semantics](https://mlsanity.com/paper/2407.15663/) (2024)
- [GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2410.00299/) (2024)
- [MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions](https://mlsanity.com/paper/2403.07593/) (2024)
- [ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images](https://mlsanity.com/paper/2503.04475/) (2025)
- [VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition](https://mlsanity.com/paper/2403.14594/) (2024)
- [A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation](https://mlsanity.com/paper/2302.14511/) (2023)
- [Instance-free Text to Point Cloud Localization with Relative Position Awareness](https://mlsanity.com/paper/2404.17845/) (2024)
- [Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps](https://mlsanity.com/paper/2301.08957/) (2023)
- [SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognition](https://mlsanity.com/paper/2306.01205/) (2023)
- [Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition](https://mlsanity.com/paper/2309.00168/) (2023)
- [OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition](https://mlsanity.com/paper/2405.07966/) (2024)
- [L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery](https://mlsanity.com/paper/2503.11245/) (2025)
- [Vehicle-Scene Interaction: A Text-Driven 3D Lidar Place Recognition Method for Autonomous Driving](https://mlsanity.com/paper/2503.18035/) (2025)
- [LifelongPR: Lifelong point cloud place recognition based on sample replay and prompt learning](https://mlsanity.com/paper/2507.10034/) (2025)
- [BPT: Binary Point Cloud Transformer for Place Recognition](https://mlsanity.com/paper/2303.01166/) (2023)
- [M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments](https://mlsanity.com/paper/2508.17044/) (2025)
- [SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localization](https://mlsanity.com/paper/2601.03579/) (2026)

## Abstract (arXiv)

3D point cloud-based place recognition is highly demanded by autonomous driving in GPS-challenged environments and serves as an essential component (i.e. loop-closure detection) in lidar-based SLAM systems. This paper proposes a novel approach, named NDT-Transformer, for realtime and large-scale place recognition using 3D point clouds. Specifically, a 3D Normal Distribution Transform (NDT) representation is employed to condense the raw, dense 3D point cloud as probabilistic distributions (NDT cells) to provide the geometrical shape description. Then a novel NDT-Transformer network learns a global descriptor from a set of 3D NDT cell representations. Benefiting from the NDT representation and NDT-Transformer network, the learned global descriptors are enriched with both geometrical and contextual information. Finally, descriptor retrieval is achieved using a query-database for place recognition. Compared to the state-of-the-art methods, the proposed approach achieves an improvement of 7.52% on average top 1 recall and 2.73% on average top 1% recall on the Oxford Robotcar benchmark.