# Joint Multi-Condition Representation Modelling via Matrix Factorisation for Visual Place Recognition

arXiv: https://arxiv.org/abs/2510.17739 · HTML: https://mlsanity.com/paper/2510.17739/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [Using Deep Learning and Google Street View to Estimate the Demographic Makeup of the US](https://mlsanity.com/paper/1702.06683/) (2017)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [MegaLoc: One Retrieval to Place Them All](https://mlsanity.com/paper/2502.17237/) (2025)
- [Event-based visual place recognition with ensembles of temporal windows](https://mlsanity.com/paper/2006.02826/) (2020)
- [Viewpoint Invariant Dense Matching for Visual Geolocalization](https://mlsanity.com/paper/2109.09827/) (2021)
- [Single-View Place Recognition under Seasonal Changes](https://mlsanity.com/paper/1808.06516/) (2018)
- [Learning Sequential Descriptors for Sequence-based Visual Place Recognition](https://mlsanity.com/paper/2207.03868/) (2022)
- [Hierarchical Multi-Process Fusion for Visual Place Recognition](https://mlsanity.com/paper/2002.03895/) (2020)
- [Intelligent Reference Curation for Visual Place Recognition via Bayesian Selective Fusion](https://mlsanity.com/paper/2010.09228/) (2020)
- [Estimating city-level travel patterns using street imagery: a case study of using Google Street View in Britain](https://mlsanity.com/paper/1802.02915/) (2018)
- [PanoVPR: Towards Unified Perspective-to-Equirectangular Visual Place Recognition via Sliding Windows across the Panoramic View](https://mlsanity.com/paper/2303.14095/) (2023)
- [Panorama to panorama matching for location recognition](https://mlsanity.com/paper/1704.06591/) (2017)
- [On Motion Blur and Deblurring in Visual Place Recognition](https://mlsanity.com/paper/2412.07751/) (2024)
- [Range and Bird's Eye View Fused Cross-Modal Visual Place Recognition](https://mlsanity.com/paper/2502.11742/) (2025)

## Abstract (arXiv)

We address multi-reference visual place recognition (VPR), where reference sets captured under varying conditions are used to improve localisation performance. While deep learning with large-scale training improves robustness, increasing data diversity and model complexity incur extensive computational cost during training and deployment. Descriptor-level fusion via voting or aggregation avoids training, but often targets multi-sensor setups or relies on heuristics with limited gains under appearance and viewpoint change. We propose a training-free, descriptor-agnostic approach that jointly models places using multiple reference descriptors via matrix decomposition into basis representations, enabling projection-based residual matching. We also introduce SotonMV, a structured benchmark for multi-viewpoint VPR. On multi-appearance data, our method improves Recall@1 by up to ~18% over single-reference and outperforms multi-reference baselines across appearance and viewpoint changes, with gains of ~5% on unstructured data, demonstrating strong generalisation while remaining lightweight.