SOURCE-LINKED INTELLIGENCE

XDG: Accelerated Visual Disambiguation

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically distinct surfaces can produce incorrect image matches and degrade reconstruction quality. Previous work mitigates this issue with geometry-aware foundation-model features, but places a heavy transformer classifier on top of the backbone, making large-scale disambiguation expensive. We introduce XDG, an efficient visual disambiguation model designed for scalable SfM. Our key observation is that a 3D foundation model already performs the cross-view geo

Read original source ↗ Open in workspace

recordType

paper

region

Global