Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Mohamed Boussaha"'
Autor:
Loic Landrieu, Mohamed Boussaha
Publikováno v:
ICML Workshop on Learning and Reasoning with Graph-Structured Representations
ICML Workshop on Learning and Reasoning with Graph-Structured Representations, Jun 2019, Long Beach (CA), United States
HAL
ICML Workshop on Learning and Reasoning with Graph-Structured Representations, Jun 2019, Long Beach (CA), United States
HAL
We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured by a ground truth segmentation. It promotes learning vertex embeddings
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12c2f1c074f66bac67ebdcb71af4c218
https://hal.archives-ouvertes.fr/hal-03016114/file/1905.04014.pdf
https://hal.archives-ouvertes.fr/hal-03016114/file/1905.04014.pdf
Autor:
Loic Landrieu, Mohamed Boussaha
Publikováno v:
CVPR
CVPR, 2019, Long Beach, France
HAL
CVPR, 2019, Long Beach, France
HAL
We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents high cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5342da059092d6cde154440d4f0c22be
https://hal.archives-ouvertes.fr/hal-03016113/file/Landrieu_Point_Cloud_Oversegmentation_With_Graph-Structured_Deep_Metric_Learning_CVPR_2019_paper.pdf
https://hal.archives-ouvertes.fr/hal-03016113/file/Landrieu_Point_Cloud_Oversegmentation_With_Graph-Structured_Deep_Metric_Learning_CVPR_2019_paper.pdf
Publikováno v:
RFIAP 2018, Reconnaissance des Formes, Image, Apprentissage et Perception
RFIAP 2018, Reconnaissance des Formes, Image, Apprentissage et Perception, Jun 2018, Marne la Vallée, France
HAL
RFIAP 2018, Reconnaissance des Formes, Image, Apprentissage et Perception, Jun 2018, Marne la Vallée, France
HAL
International audience; Dans cet article nous présentons un cadre entièrement au-tomatique pour la reconstruction d'un maillage, sa textu-ration et sa sémantisation à large échelle à partir de scans LiDAR et d'images orientées de scènes urbai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::185c14ba7dca0f6ea6d795f38ffff78b
https://hal.science/hal-02552591/document
https://hal.science/hal-02552591/document
Publikováno v:
ISPRS 2018-International Society for Photogrammetry and Remote Sensing
ISPRS 2018-International Society for Photogrammetry and Remote Sensing, Mar 2018, Istanbul, Turkey. pp.49-56, ⟨10.5194/isprs-annals-IV-2-49-2018⟩
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol IV-2, Pp 49-56 (2018)
ISPRS 2018-International Society for Photogrammetry and Remote Sensing, Mar 2018, Istanbul, Turkey. pp.49-56, ⟨10.5194/isprs-annals-IV-2-49-2018⟩
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol IV-2, Pp 49-56 (2018)
The representation of 3D geometric and photometric information of the real world is one of the most challenging and extensively studied research topics in the photogrammetry and robotics communities. In this paper, we present a fully automatic framew
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6fea9dff6f7ae79fbe5dcefb9c95764e
https://hal.archives-ouvertes.fr/hal-01764547/document
https://hal.archives-ouvertes.fr/hal-01764547/document