Hypevpr: Exploring Hyperbolic Space For Perspective To Equirectangular Visual Place Recognition

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 approa

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywoo2025hypevpr

Related papers

• Panovpr: Towards Unified Perspective-to-equirectangular Visual Place Recognition Via Sliding Windows Across The Panoramic View (2023)10.18
• Hlformer: Enhancing Partially Relevant Video Retrieval With Hyperbolic Learning (2025)3.50
• Learning Visual Hierarchies In Hyperbolic Space For Image Retrieval (2024)0.00
• Unipr-3d: Towards Universal Visual Place Recognition With Visual Geometry Grounded Transformer (2025)2.95
• Hierloc: Hyperbolic Entity Embeddings For Hierarchical Visual Geolocation (2026)0.00
• Eigenplaces: Training Viewpoint Robust Models For Visual Place Recognition (2023)15.46
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• Evaluation Of Visual Place Recognition Methods For Image Pair Retrieval In 3D Vision And Robotics (2026)0.00