AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

AstroLoc: Robust Space to Ground Image Localizer

Gabriele Berton, Alex Stoken, Carlo Masone

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 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
add unsupervised mining loss (Solution 3) to the pair loss (ablation)AstroLoc · Texas-Lrecall@1: 83.6 -> 91.1Improved
add unsupervised mining loss (Solution 3) to the pair loss (ablation)AstroLoc · Alps-Lrecall@1: 87.2 -> 94.6Improved
add database clustering loss (Solution 2) to the pair loss (ablation)AstroLoc · Texas-Lrecall@1: 83.6 -> 86.5Improved
add naive sampling loss (Solution 1) to the pair loss (ablation)AstroLoc · Texas-Lrecall@1: 83.6 -> 84.0No clear effect
add naive sampling loss (Solution 1) to the pair loss (ablation)AstroLoc · Alps-Lrecall@100: 98.2 -> 98.0No clear effect
add pair loss to unsupervised mining alone (ablation)AstroLoc · Texas-Lrecall@1: 82.2 -> 91.1Improved
sample clusters by query distribution (Solution 3) instead of uniform clustering (Solution 2), loss alone (ablation)AstroLoc · Texas-Lrecall@1: 72.4 -> 82.2Improved
use AstroLoc training instead of EarthLoc++ (same architecture)EarthLoc++ · Texas (EarthLoc test set)recall@1: 80.0 -> 96.1Improved
use AstroLoc training instead of EarthLoc++ (same architecture)EarthLoc++ · Texas-L (extended test set)recall@1: 72.4 -> 91.1Improved
use AstroLoc-tiny (27M parameters, 512-d) instead of full AstroLocAstroLoc · Lost-in-Space (VINSat queries)recall@1: 52.7 -> 36.7Hurt
use AstroLoc on worldwide search instead of EarthLocEarthLoc · Worldwide search (881k database)recall@100: 66.6 -> 96.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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