Passer à la navigation principale Passer à la recherche Passer au contenu principal

MACARONS: Mapping and Coverage Anticipation with RGB Online Self-Supervision

  • Université Gustave Eiffel

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

We introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only. This is closely related to the Next Best View problem (NBV), where one has to identify where to move the camera next to improve the coverage of an unknown scene. However, most of the current NBV methods rely on depth sensors, need 3D supervision and/or do not scale to large scenes. Our method requires only a color camera and no 3D supervision. It simultaneously learns in a self-supervised fashion to predict a 'volume occupancy field' from color images and, from this field, to predict the NBV. Thanks to this approach, our method performs well on new scenes as it is not biased towards any training 3D data. We demonstrate this on a recent dataset made of various 3D scenes and show it performs even better than recent methods requiring a depth sensor, which is not a realistic assumption for outdoor scenes captured with a flying drone.

langue originaleAnglais
titreProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
EditeurIEEE Computer Society
Pages940-951
Nombre de pages12
ISBN (Electronique)9798350301298
ISBN (imprimé)9798350301298
Les DOIs
étatPublié - 1 janv. 2023
Modification externeOui
Evénement2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada
Durée: 18 juin 202322 juin 2023

Série de publications

NomProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2023-June
ISSN (imprimé)1063-6919

Une conférence

Une conférence2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Pays/TerritoireCanada
La villeVancouver
période18/06/2322/06/23

Empreinte digitale

Examiner les sujets de recherche de « MACARONS: Mapping and Coverage Anticipation with RGB Online Self-Supervision ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation