AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

Suhan Woo, Seongwon Lee, Jinwoo Jang, Euntai Kim

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
embed descriptors in hyperbolic (Poincare ball) space instead of Euclidean space (ablation)2-level HAM hierarchy · Pitts250k-P2ERecall@1: 9.2 -> 14.9Improved
add Euclidean triplet loss on window-level descriptors (ablation)HypeVPR-O · Pitts250k-P2ERecall@1: 32.0 -> 66.5Improved
add hierarchical triplet loss (ablation)HypeVPR-O · Pitts250k-P2ERecall@1: 50.8 -> 66.5Improved
add hyperbolic triplet loss (ablation)HypeVPR-O · Pitts250k-P2ERecall@1: 64.3 -> 66.5Improved
fuse top-level and lowest-level scores (HypeVPR-L) instead of lowest-level sliding window only (ablation)HypeVPR · Pitts250k-P2ERecall@1: 80.6 -> 81.2Improved
use hierarchical retrieval (HypeVPR-B) instead of EigenPlace exhaustive window searchEigenPlace backbone · Pitts250k-P2Eretrieval time per query (ms): 90.5 -> 17.9Improved
use only the top-level descriptor (no reranking) (ablation)HypeVPR · Pitts250k-P2ERecall@1: 81.2 -> 66.5Hurt
use HypeVPR-L instead of PanoVPRx16 on ConvNeXt-SP2E baseline · Pitts250K-P2ERecall@1: 40.3 -> 43.4Improved
use HypeVPR-L instead of PanoVPRx16 on Swin-TP2E baseline · Pitts250K-P2ERecall@1: 33.6 -> 32.5Mixed
HypeVPR-L versus SALAD on large-scale SF-XLP2P baseline · SF-XL testRecall@1: 88.6 -> 85.2Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy