# Loop closure detection using local 3D deep descriptors

arXiv: https://arxiv.org/abs/2111.00440 · HTML: https://mlsanity.com/paper/2111.00440/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 31 Oct 2021.

## Builds on (most cited first, 14 of 14)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [OverlapNet: Loop Closing for LiDAR-based SLAM](https://mlsanity.com/paper/2105.11344/) (2021)
- [SegMatch: Segment based loop-closure for 3D point clouds](https://mlsanity.com/paper/1609.07720/) (2016)
- [SegMap: Segment-based mapping and localization using data-driven descriptors](https://mlsanity.com/paper/1909.12837/) (2019)
- [LiDAR Iris for Loop-Closure Detection](https://mlsanity.com/paper/1912.03825/) (2019)
- [Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection](https://mlsanity.com/paper/2003.05656/) (2020)
- [Distinctive 3D local deep descriptors](https://mlsanity.com/paper/2009.00258/) (2020)
- [LocNet: Global localization in 3D point clouds for mobile vehicles](https://mlsanity.com/paper/1712.02165/) (2017)
- [Have I been here before? Learning to Close the Loop with LiDAR Data in Graph-Based SLAM](https://mlsanity.com/paper/2103.06713/) (2021)

## Built on by (most cited first, 8 of 8)

- [Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration](https://mlsanity.com/paper/2303.13290/) (2023)
- [Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation](https://mlsanity.com/paper/2308.14619/) (2023)
- [Overlap-guided Gaussian Mixture Models for Point Cloud Registration](https://mlsanity.com/paper/2210.09836/) (2022)
- [Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2210.02798/) (2022)
- [Distilling 3D distinctive local descriptors for 6D pose estimation](https://mlsanity.com/paper/2503.15106/) (2025)
- [PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding](https://mlsanity.com/paper/2307.15692/) (2023)
- [PNE-SGAN: Probabilistic NDT-Enhanced Semantic Graph Attention Network for LiDAR Loop Closure Detection](https://mlsanity.com/paper/2504.08280/) (2025)
- [GPI-Net: Gestalt-Guided Parallel Interaction Network via Orthogonal Geometric Consistency for Robust Point Cloud Registration](https://mlsanity.com/paper/2507.14452/) (2025)

## Abstract (arXiv)

We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds). L3Ds are emerging compact representations of patches extracted from point clouds that are learnt from data using a deep learning algorithm. We propose a novel overlap measure for loop detection by computing the metric error between points that correspond to mutually-nearest-neighbour descriptors after registering the loop candidate point cloud by its estimated relative pose. This novel approach enables us to accurately detect loops and estimate six degrees-of-freedom poses in the case of small overlaps. We compare our L3D-based loop closure approach with recent approaches on LiDAR data and achieve state-of-the-art loop closure detection accuracy. Additionally, we embed our loop closure approach in RESLAM, a recent edge-based SLAM system, and perform the evaluation on real-world RGBD-TUM and synthetic ICL datasets. Our approach enables RESLAM to achieve a better localisation accuracy compared to its original loop closure strategy. Our project page is available at github.com/yiming107/l3d_loop_closure.