Eigenplaces: Training Viewpoint Robust Models For Visual Place Recognition

Abstract

Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a large database of geotagged photos, using learned global descriptors. A major challenge in this task is recognizing places seen from different viewpoints. To overcome this limitation, we propose a new method, called EigenPlaces, to train our neural network on images from different point of views, which embeds viewpoint robustness into the learned global descriptors. The underlying idea is to cluster the training data so as to explicitly present the model with different views of the same points of interest. The selection of this points of interest is done without the need for extra supervision. We then present experiments on the most comprehensive set of datasets in literature, finding that EigenPlaces is able to outperform previous state of the art on

Stats

• citations114
• S2 citations—
• github stars0
• HF likes0
• heat score15.46
• arxiv keyberton2023eigenplaces

Related papers

• Graph-based Non-linear Least Squares Optimization For Visual Place Recognition In Changing Environments (2020)7.16
• Are Local Features All You Need For Cross-domain Visual Place Recognition? (2023)13.80
• Spatio-semantic Convnet-based Visual Place Recognition (2019)10.21
• Place Recognition: An Overview Of Vision Perspective (2017)9.92
• Regressing Transformers For Data-efficient Visual Place Recognition (2024)3.58
• Probabilistic Visual Place Recognition For Hierarchical Localization (2021)11.08
• Embodiedplace: Learning Mixture-of-features With Embodied Constraints For Visual Place Recognition (2025)0.00
• Boq: A Place Is Worth A Bag Of Learnable Queries (2024)16.09