# Viewpoint Invariant Dense Matching for Visual Geolocalization

arXiv: https://arxiv.org/abs/2109.09827 · HTML: https://mlsanity.com/paper/2109.09827/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Learning Less is More - 6D Camera Localization via 3D Surface Regression](https://mlsanity.com/paper/1711.10228/) (2017)
- [Convolutional neural network architecture for geometric matching](https://mlsanity.com/paper/1703.05593/) (2017)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)
- [Learning to Navigate in Cities Without a Map](https://mlsanity.com/paper/1804.00168/) (2018)
- [SOLAR: Second-Order Loss and Attention for Image Retrieval](https://mlsanity.com/paper/2001.08972/) (2020)
- [Adaptive-Attentive Geolocalization from few queries: a hybrid approach](https://mlsanity.com/paper/2010.06897/) (2020)
- [WarpNet: Weakly Supervised Matching for Single-view Reconstruction](https://mlsanity.com/paper/1604.05592/) (2016)
- [Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing](https://mlsanity.com/paper/1811.10907/) (2018)
- [Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings](https://mlsanity.com/paper/2008.05785/) (2020)
- [Self-localization from Images with Small Overlap](https://mlsanity.com/paper/1603.00993/) (2016)

## Built on by (most cited first, 30 of 36)

- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment](https://mlsanity.com/paper/2312.06960/) (2023)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition](https://mlsanity.com/paper/2402.14505/) (2024)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [PATS: Patch Area Transportation with Subdivision for Local Feature Matching](https://mlsanity.com/paper/2303.07700/) (2023)
- [Adaptive Assignment for Geometry Aware Local Feature Matching](https://mlsanity.com/paper/2207.08427/) (2022)
- [Adaptive Spot-Guided Transformer for Consistent Local Feature Matching](https://mlsanity.com/paper/2303.16624/) (2023)
- [On the Estimation of Image-matching Uncertainty in Visual Place Recognition](https://mlsanity.com/paper/2404.00546/) (2024)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition](https://mlsanity.com/paper/2502.16601/) (2025)
- [Long-range UAV Thermal Geo-localization with Satellite Imagery](https://mlsanity.com/paper/2306.02994/) (2023)
- [AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition](https://mlsanity.com/paper/2310.05184/) (2023)
- [Structured Epipolar Matcher for Local Feature Matching](https://mlsanity.com/paper/2303.16646/) (2023)
- [Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era](https://mlsanity.com/paper/2511.06024/) (2025)
- [Deep Homography Estimation for Visual Place Recognition](https://mlsanity.com/paper/2402.16086/) (2024)
- [SegMASt3R: Geometry Grounded Segment Matching](https://mlsanity.com/paper/2510.05051/) (2025)
- [Visual place recognition for aerial imagery: A survey](https://mlsanity.com/paper/2406.00885/) (2024)
- [SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models](https://mlsanity.com/paper/2506.13073/) (2025)
- [MMS-VPR: A Fine-Grained Multimodal Street-Level Visual Place Recognition Dataset and Evaluation Benchmark for Dense Pedestrian Environments](https://mlsanity.com/paper/2505.12254/) (2025)
- [Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition](https://mlsanity.com/paper/2510.13464/) (2025)
- [Active Domain-Invariant Self-Localization Using Ego-Centric and World-Centric Maps](https://mlsanity.com/paper/2204.10497/) (2022)
- [CoPR: Towards Accurate Visual Localization With Continuous Place-descriptor Regression](https://mlsanity.com/paper/2304.07426/) (2023)
- [Collaborative Visual Place Recognition through Federated Learning](https://mlsanity.com/paper/2404.13324/) (2024)
- [Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition](https://mlsanity.com/paper/2604.22390/) (2026)
- [Skill-Conditioned Visual Geolocation for Vision-Language Models](https://mlsanity.com/paper/2604.09025/) (2026)
- [NPR: Nocturnal Place Recognition in Streets](https://mlsanity.com/paper/2304.00276/) (2023)

## Abstract (arXiv)

In this paper we propose a novel method for image matching based on dense local features and tailored for visual geolocalization. Dense local features matching is robust against changes in illumination and occlusions, but not against viewpoint shifts which are a fundamental aspect of geolocalization. Our method, called GeoWarp, directly embeds invariance to viewpoint shifts in the process of extracting dense features. This is achieved via a trainable module which learns from the data an invariance that is meaningful for the task of recognizing places. We also devise a new self-supervised loss and two new weakly supervised losses to train this module using only unlabeled data and weak labels. GeoWarp is implemented efficiently as a re-ranking method that can be easily embedded into pre-existing visual geolocalization pipelines. Experimental validation on standard geolocalization benchmarks demonstrates that GeoWarp boosts the accuracy of state-of-the-art retrieval architectures. The code and trained models are available at https://github.com/gmberton/geo_warp