SimLOG: Simultaneous Local-Global Feature Learning for 3D Object Detection in Indoor Point Clouds

The acquisition of both local and global features from irregular point clouds is crucial for 3D object detection (3DOD). Current mainstream 3D detectors neglect significant local features during pooling operations or disregard many global features of the overall scene context. This paper proposes ne...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on intelligent transportation systems 2024-12, Vol.25 (12), p.19482-19495
Hauptverfasser:	Wei, Mingqiang, Chen, Baian, Nan, Liangliang, Xie, Haoran, Gu, Lipeng, Lu, Dening, Lee Wang, Fu, Li, Qing
Format:	Artikel
Sprache:	eng
Schlagworte:	3D object detection Aggregates dynamic points interaction Feature extraction global context aggregation Object detection Point cloud compression Representation learning SimLOG Three-dimensional displays Transformers
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!