Désiré Sidibé — accepted AI-conference papers

2025

ViiNeuS: Volumetric Initialization for Implicit Neural Surface Reconstruction of Urban Scenes with Limited Image Overlap

Hala Djeghim, Nathan Piasco, Moussab Bennehar, Luis Roldao, Dzmitry Tsishkou, Désiré Sidibé

CVPR 2025poster

Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and limited visual observation overlap.Hence, to achieve accurate reconstructions…

Cited by 0 Source ↗PDF ↗Scholar ↗

2019

Learning Scene Geometry for Visual Localization in Challenging Conditions

Nathan Piasco, Désiré Sidibé, Valérie Gouet-Brunet, Cédric Demonceaux

ICRA 2019poster

We propose a new approach for outdoor large scale image based localization that can deal with challenging scenarios like cross-season, cross-weather, day/night and long-term localization. The key component of our method is a new learned global image descriptor, that can effectively benefit from scen…

Cited by 48 Source ↗Scholar ↗