SOURCE-LINKED INTELLIGENCE

AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global