# Augmenting Visual Place Recognition with Structural Cues

arXiv: https://arxiv.org/abs/2003.00278 · HTML: https://mlsanity.com/paper/2003.00278/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Feb 2020.

## Built on by (most cited first, 23 of 23)

- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition](https://mlsanity.com/paper/2104.05327/) (2021)
- [AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition](https://mlsanity.com/paper/2111.11739/) (2021)
- [LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization](https://mlsanity.com/paper/2312.16648/) (2023)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [Place recognition survey: An update on deep learning approaches](https://mlsanity.com/paper/2106.10458/) (2021)
- [STUN: Self-Teaching Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.01851/) (2022)
- [General Place Recognition Survey: Towards the Real-world Autonomy Age](https://mlsanity.com/paper/2209.04497/) (2022)
- [AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition](https://mlsanity.com/paper/2106.09637/) (2021)
- [DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition](https://mlsanity.com/paper/2312.10616/) (2023)
- [A Light Touch Approach to Teaching Transformers Multi-view Geometry](https://mlsanity.com/paper/2211.15107/) (2022)
- [LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control](https://mlsanity.com/paper/2401.04855/) (2024)
- [BEV2PR: BEV-Enhanced Visual Place Recognition with Structural Cues](https://mlsanity.com/paper/2403.06600/) (2024)
- [VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2409.19293/) (2024)
- [Visual Place Representation and Recognition from Depth Images](https://mlsanity.com/paper/2112.13707/) (2021)
- [FusionLoc: Camera-2D LiDAR Fusion Using Multi-Head Self-Attention for End-to-End Serving Robot Relocalization](https://mlsanity.com/paper/2303.06872/) (2023)
- [LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2407.06730/) (2024)
- [PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion](https://mlsanity.com/paper/2410.04939/) (2024)
- [CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement](https://mlsanity.com/paper/2311.11604/) (2023)
- [MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity](https://mlsanity.com/paper/2505.17591/) (2025)
- [SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition](https://mlsanity.com/paper/2106.11481/) (2021)
- [SPOT: Point Cloud Based Stereo Visual Place Recognition for Similar and Opposing Viewpoints](https://mlsanity.com/paper/2404.12339/) (2024)

## Abstract (arXiv)

In this paper, we propose to augment image-based place recognition with structural cues. Specifically, these structural cues are obtained using structure-from-motion, such that no additional sensors are needed for place recognition. This is achieved by augmenting the 2D convolutional neural network (CNN) typically used for image-based place recognition with a 3D CNN that takes as input a voxel grid derived from the structure-from-motion point cloud. We evaluate different methods for fusing the 2D and 3D features and obtain best performance with global average pooling and simple concatenation. On the Oxford RobotCar dataset, the resulting descriptor exhibits superior recognition performance compared to descriptors extracted from only one of the input modalities, including state-of-the-art image-based descriptors. Especially at low descriptor dimensionalities, we outperform state-of-the-art descriptors by up to 90%.