AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels
Neural map matchers estimate an image's 3-DoF pose relative to a 2D map. These models are trained on large-scale datasets of geo-referenced images, whose position and heading labels often contain noise that affects the trained models. To address this, we present AutoCompass, a supervision approach for training neural map matchers from inaccurate absolute pose labels. First, we show that heading labels are unnecessary: trained from raw GPS labels, models learn to predict accurate headings, automatically. Second, defining a tolerance region around raw GPS improves positional accuracy. Third, if
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 84%amitness/learning →
“Fuzzy title match (0.92): “AutoCompass: Accurate Visual Localization on Public Maps by ” ≈ “amitness/learning””
- LinkedLinked via arxiv author · 85%Javier Tirado-Garín →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”
- LinkedLinked via arxiv author · 85%Alan Savio Paul →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”
- LinkedLinked via arxiv author · 85%Shuai Chen →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”
- LinkedLinked via arxiv author · 85%Axel Barroso-Laguna →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”
- LinkedLinked via arxiv author · 85%Tommaso Cavallari →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”
- LinkedLinked via arxiv author · 85%Daniyar Turmukhambetov →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”
- LinkedLinked via arxiv author · 85%Victor Adrian Prisacariu →
“AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels”