# Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images Source: [Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:27:25.007Z Authors: Xindi Wu, KwunFung Lau, Francesco Ferroni, Aljo\\v{s}a O\\v{s}ep, Deva Ramanan Published: 2023-01-10T22:05:35.000Z ## Abstract Self-driving vehicles rely on urban street maps for autonomous navigation. In this paper, we introduce Pix2Map, a method for inferring urban street map topology directly from ego-view images, as needed to continually update and expand existing maps. This is a challenging task, as we need to infer a complex urban road topology directly from raw image data. The main insight of this paper is that this problem can be posed as cross-modal retrieval by learning a joint, cross-modal embedding space for images and existing maps, represented as discrete graphs that encode the topological layout of the visual surroundings. We conduct our experimental evaluation using the Argoverse dataset and show that it is indeed possible to accurately retrieve street maps corresponding to both seen and unseen roads solely from image data. Moreover, we show that our retrieved maps can be used to update or expand existing maps and even show proof-of-concept results for visual localization and image retrieval from spatial graphs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [HD Map Reconstruction on Argoverse frontal 50m x 50m (test)](): HD Map Reconstruction; Argoverse frontal 50m x 50m (test); Chamfer Distance: 208.82. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()