# Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems

arXiv: https://arxiv.org/abs/2104.10067 · HTML: https://mlsanity.com/paper/2104.10067/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2021.

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

- [SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs](https://mlsanity.com/paper/2404.00469/) (2024)
- [I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections](https://mlsanity.com/paper/2303.01043/) (2023)
- [General Place Recognition Survey: Towards the Real-world Autonomy Age](https://mlsanity.com/paper/2209.04497/) (2022)
- [MSSPlace: Multi-Sensor Place Recognition with Visual and Text Semantics](https://mlsanity.com/paper/2407.15663/) (2024)
- [ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition](https://mlsanity.com/paper/2403.18762/) (2024)
- [Visual Localization in 3D Maps: Comparing Point Cloud, Mesh, and NeRF Representations](https://mlsanity.com/paper/2408.11966/) (2024)
- [Heterogeneous LiDAR Early Fusion and Learned Re-Ranking Strategy for Robust Long-Term Place Recognition in Unstructured Environments](https://mlsanity.com/paper/2606.13503/) (2026)
- [M3GA-Wild: A Large-Scale Dataset and Benchmark for Multi-Modal Multi-session Ground-to-Aerial Place Recognition in Forests](https://mlsanity.com/paper/2609.23003/) (2026)

## Abstract (arXiv)

In this paper, we propose a robust end-to-end multi-modal pipeline for place recognition where the sensor systems can differ from the map building to the query. Our approach operates directly on images and LiDAR scans without requiring any local feature extraction modules. By projecting the sensor data onto the unit sphere, we learn a multi-modal descriptor of partially overlapping scenes using a spherical convolutional neural network. The employed spherical projection model enables the support of arbitrary LiDAR and camera systems readily without losing information. Loop closure candidates are found using a nearest-neighbor lookup in the embedding space. We tackle the problem of correctly identifying the closest place by correlating the candidates' power spectra, obtaining a confidence value per prospect. Our estimate for the correct place corresponds then to the candidate with the highest confidence. We evaluate our proposal w.r.t. state-of-the-art approaches in place recognition using real-world data acquired using different sensors. Our approach can achieve a recall that is up to 10% and 5% higher than for a LiDAR- and vision-based system, respectively, when the sensor setup differs between model training and deployment. Additionally, our place selection can correctly identify up to 95% matches from the candidate set.