# PADLoC: LiDAR-Based Deep Loop Closure Detection and Registration Using Panoptic Attention

arXiv: https://arxiv.org/abs/2209.09699 · HTML: https://mlsanity.com/paper/2209.09699/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2022.

## Built on by (most cited first, 12 of 12)

- [Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM](https://mlsanity.com/paper/2309.08086/) (2023)
- [CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration](https://mlsanity.com/paper/2402.00129/) (2024)
- [RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps](https://mlsanity.com/paper/2309.09875/) (2023)
- [ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency](https://mlsanity.com/paper/2407.09862/) (2024)
- [SAGE-ICP: Semantic Information-Assisted ICP](https://mlsanity.com/paper/2310.07237/) (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)
- [Designing for Difference: How Human Characteristics Shape Perceptions of Collaborative Robots](https://mlsanity.com/paper/2507.16480/) (2025)
- [RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline](https://mlsanity.com/paper/2309.07094/) (2023)
- [Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation](https://mlsanity.com/paper/2309.09934/) (2023)
- [WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Research](https://mlsanity.com/paper/2402.19059/) (2024)
- [Learning Lane Graphs from Aerial Imagery Using Transformers](https://mlsanity.com/paper/2407.05687/) (2024)

## Abstract (arXiv)

A key component of graph-based SLAM systems is the ability to detect loop closures in a trajectory to reduce the drift accumulated over time from the odometry. Most LiDAR-based methods achieve this goal by using only the geometric information, disregarding the semantics of the scene. In this work, we introduce PADLoC for joint loop closure detection and registration in LiDAR-based SLAM frameworks. We propose a novel transformer-based head for point cloud matching and registration, and to leverage panoptic information during training time. In particular, we propose a novel loss function that reframes the matching problem as a classification task for the semantic labels and as a graph connectivity assignment for the instance labels. During inference, PADLoC does not require panoptic annotations, making it more versatile than other methods. Additionally, we show that using two shared matching and registration heads with their source and target inputs swapped increases the overall performance by enforcing forward-backward consistency. We perform extensive evaluations of PADLoC on multiple real-world datasets demonstrating that it achieves state-of-the-art results. The code of our work is publicly available at http://padloc.cs.uni-freiburg.de.