← Search

Ahmed Samy Nassar

2 accepted papers

2020

GeoGraph: Graph-based multi-view object detection with geometric cues end-to-end

ECCV 2020poster

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 out-put their geographic posit…

Cited by 33SourcePDFScholar
2019

Simultaneous Multi-View Instance Detection With Learned Geometric Soft-Constraints

ICCV 2019poster

We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes in viewpoint, lighting conditions, high similarity of neighbouring objects, and…

Cited by 35PDFScholar