# GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end

Source: [GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end](<https://www.sota2.com/research/paper/68fa673f1e209131cea15360>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:10:14.206Z

Authors: Ahmed Samy Nassar, Stefano D'Aronco, S\\'ebastien Lef\\\`evre, Jan D. Wegner

Published: 2020-03-23T09:40:35.000Z

## Abstract

In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object. Our method relies on a Graph Neural Network (GNN) to, detect all objects and output their geographic positions given images and approximate camera poses as input. Our GNN simultaneously models relative pose and image evidence, and is further able to deal with an arbitrary number of input views. Our method is robust to occlusion, with similar appearance of neighboring objects, and severe changes in viewpoints by jointly reasoning about visual image appearance and relative pose. Experimental evaluation on two challenging, large-scale datasets and comparison with state-of-the-art methods show significant and systematic improvements both in accuracy and efficiency, with 2-6% gain in detection and re-ID average precision as well as 8x reduction of training time.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2003.10151>)

[PDF](<https://arxiv.org/pdf/2003.10151.pdf>)
