AI Paper Atlas

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

Towards Visual Localization Interoperability: Cross-Feature for Collaborative Visual Localization and Mapping

Alberto Jaenal, Paula Carbó Cubero, José Araújo, André Mateus

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2 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
Use Cross-Feature patch-based training instead of Cross-DescriptorSIFT map, SuperPoint query · Aachen Day (0.25m, 2deg)% localized queries: 20.4 -> 56.3Improved
Use Cross-Feature instead of Cross-Descriptor with a different detector (OrFAST:BRIEF)SuperPoint map, ORB query · Aachen Day (0.25m, 2deg)% localized queries: 1.0 -> 13.5Improved
Use Cross-Feature instead of Cross-Descriptor on CambridgeSIFT map, SuperPoint query · Cambridge GreatCourtMedian position error (m): 0.96 -> 0.43Improved
Use Cross-Feature instead of Cross-Descriptor on 7ScenesSIFT map, SuperPoint query · 7Scenes StairsMedian position error (cm): 23.98 -> 20.62Improved
Use Cross-Feature instead of image reconstructionSIFT map, SuperPoint query · Aachen Day (0.25m, 2deg)% localized queries: 34.0 -> 56.3Improved
Use Cross-Feature instead of image reconstructionSuperPoint map, SIFT query · Aachen Day (0.25m, 2deg)% localized queries: 77.8 -> 43.1Hurt
Use Cross-Feature instead of geometry-only GoMatchSuperPoint map, SIFT query · Aachen Day (0.25m, 2deg)% localized queries: 0.2 -> 43.1Improved
Use heterogeneous query features instead of homogeneous SIFTCFemb, SIFT map · Aachen Day (0.25m, 2deg)% localized queries: 80.8 -> 56.3Hurt
Change query feature from SuperPoint to DISKCFemb, SIFT map · 7Scenes StairsMedian position error (cm): 20.62 -> 48.19Hurt
Change query from ORB to SuperPoint on SuperPoint-map Aachen nightCFemb · Aachen Night (0.25m, 2deg)% localized queries: 17.3 -> 6.1Hurt
Use collaborative merged map instead of SIFT-only mapCFemb, query SuperPoint · Cambridge GreatCourtMedian position error (m): 0.43 -> 0.30Improved
Use Cross-Feature on collaborative map instead of Cross-Descriptorquery SuperPoint · Cambridge GreatCourt (collaborative)Median position error (m): 0.85 -> 0.30Improved

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