# Open-RadVLAD: Fast and Robust Radar Place Recognition

arXiv: https://arxiv.org/abs/2401.15380 · HTML: https://mlsanity.com/paper/2401.15380/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 27 Jan 2024.

## Builds on (most cited first, 16 of 16)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [RADIATE: A Radar Dataset for Automotive Perception in Bad Weather](https://mlsanity.com/paper/2010.09076/) (2020)
- [Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar](https://mlsanity.com/paper/2001.10789/) (2020)
- [Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning](https://mlsanity.com/paper/2001.09438/) (2020)
- [AutoPlace: Robust Place Recognition with Single-chip Automotive Radar](https://mlsanity.com/paper/2109.08652/) (2021)
- [Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance](https://mlsanity.com/paper/2003.04699/) (2020)
- [One RING to Rule Them All: Radon Sinogram for Place Recognition, Orientation and Translation Estimation](https://mlsanity.com/paper/2204.07992/) (2022)
- [RaPlace: Place Recognition for Imaging Radar using Radon Transform and Mutable Threshold](https://mlsanity.com/paper/2307.04321/) (2023)
- [TBV Radar SLAM -- trust but verify loop candidates](https://mlsanity.com/paper/2301.04397/) (2023)
- [RadarLoc: Learning to Relocalize in FMCW Radar](https://mlsanity.com/paper/2103.11562/) (2021)
- [Contrastive Learning for Unsupervised Radar Place Recognition](https://mlsanity.com/paper/2110.02744/) (2021)
- [Large-Scale Topological Radar Localization Using Learned Descriptors](https://mlsanity.com/paper/2110.03081/) (2021)
- [Fast-MbyM: Leveraging Translational Invariance of the Fourier Transform for Efficient and Accurate Radar Odometry](https://mlsanity.com/paper/2203.00459/) (2022)

## Built on by (most cited first, 6 of 6)

- [LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition](https://mlsanity.com/paper/2504.19186/) (2025)
- [UniMPR: A Unified Framework for Multimodal Place Recognition with Heterogeneous Sensor Configurations](https://mlsanity.com/paper/2512.18279/) (2025)
- [MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity](https://mlsanity.com/paper/2505.17591/) (2025)
- [RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving](https://mlsanity.com/paper/2603.07920/) (2026)
- [Spatially Stratified Distillation for Heterogeneous Radar Place Recognition](https://mlsanity.com/paper/2606.18687/) (2026)
- [Automotive mmWave Spinning Radar Place Recognition with Spatially Gated Feature-Correlation Representation](https://mlsanity.com/paper/2609.27394/) (2026)

## Abstract (arXiv)

Radar place recognition often involves encoding a live scan as a vector and matching this vector to a database in order to recognise that the vehicle is in a location that it has visited before. Radar is inherently robust to lighting or weather conditions, but place recognition with this sensor is still affected by: (1) viewpoint variation, i.e. translation and rotation, (2) sensor artefacts or "noises". For 360-degree scanning radar, rotation is readily dealt with by in some way aggregating across azimuths. Also, we argue in this work that it is more critical to deal with the richness of representation and sensor noises than it is to deal with translational invariance - particularly in urban driving where vehicles predominantly follow the same lane when repeating a route. In our method, for computational efficiency, we use only the polar representation. For partial translation invariance and robustness to signal noise, we use only a one-dimensional Fourier Transform along radial returns. We also achieve rotational invariance and a very discriminative descriptor space by building a vector of locally aggregated descriptors. Our method is more comprehensively tested than all prior radar place recognition work - over an exhaustive combination of all 870 pairs of trajectories from 30 Oxford Radar RobotCar Dataset sequences (each approximately 10 km). Code and detailed results are provided at github.com/mttgdd/open-radvlad, as an open implementation and benchmark for future work in this area. We achieve a median of 91.52% in Recall@1, outstripping the 69.55% for the only other open implementation, RaPlace, and at a fraction of its computational cost (relying on fewer integral transforms e.g. Radon, Fourier, and inverse Fourier).