HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition

TL;DR

HypeVPR introduces a hyperbolic space-based hierarchical embedding framework for panoramic visual place recognition, effectively capturing hierarchical scene information to improve accuracy, efficiency, and robustness in matching equirectangular images.

Contribution

It proposes a novel hyperbolic embedding method with hierarchical feature aggregation for P2E visual place recognition, enabling flexible accuracy-efficiency trade-offs without extra training.

Findings

Achieves competitive recognition performance.

Reduces database storage requirements.

Speeds up retrieval process.

Abstract

Visual environments are inherently hierarchical, as a panoramic view naturally encompasses and organizes multiple perspective views within its field. Capturing this hierarchy is crucial for effective perspective-to-equirectangular (P2E) visual place recognition. In this work, we introduce HypeVPR, a hierarchical embedding framework in hyperbolic space specifically designed to address the challenges of P2E matching. HypeVPR leverages the intrinsic ability of hyperbolic space to represent hierarchical structures, allowing panoramic descriptors to encode both broad contextual information and fine-grained local details. To this end, we propose a hierarchical feature aggregation mechanism that organizes local-to-global feature representations within hyperbolic space. Furthermore, HypeVPR's hierarchical organization naturally enables flexible control over the accuracy-efficiency trade-off without additional training, while maintaining robust matching across different image types. This approach enables HypeVPR to achieve competitive performance while significantly accelerating retrieval and reducing database storage requirements. Project page: https://suhan-woo.github.io/HypeVPR/