HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition
This addresses the challenge of robust place recognition for mobile robots with diverse viewpoints, representing an incremental improvement through a novel application of hyperbolic geometry.
The paper tackles the problem of visual place recognition for mobile robots using perspective-to-equirectangular images by introducing HypeVPR, a hierarchical embedding framework in hyperbolic space that outperforms existing methods while accelerating retrieval and reducing storage requirements.
When applying Visual Place Recognition (VPR) to real-world mobile robots and similar applications, perspective-to-equirectangular (P2E) formulation naturally emerges as a suitable approach to accommodate diverse query images captured from various viewpoints. In this paper, we introduce HypeVPR, a novel hierarchical embedding framework in hyperbolic space, designed to address the unique challenges of P2E VPR. The key idea behind HypeVPR is that visual environments captured by panoramic views exhibit inherent hierarchical structures. To leverage this property, we employ hyperbolic space to represent hierarchical feature relationships and preserve distance properties within the feature space. To achieve this, we propose a hierarchical feature aggregation mechanism that organizes local-to-global feature representations within hyperbolic space. Additionally, HypeVPR adopts an efficient coarse-to-fine search strategy to enable flexible control over accuracy-efficiency trade-offs and ensure robust matching even between descriptors from different image types. This approach allows HypeVPR to outperform existing methods while significantly accelerating retrieval and reducing database storage requirements. The code and models will be released at https://github.com/suhan-woo/HypeVPR.git.