Point Transformer for Shape Classification and Retrieval of Urban Roof Point Clouds

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input distribution and cannot learn long-range dependences. Recent...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE geoscience and remote sensing letters 2022, Vol.19, p.1-5
Hauptverfasser:	Shajahan, Dimple A., Varma T., Mukund, Muthuganapathy, Ramanathan
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmark testing Benchmarks Classification Data models Datasets Deep learning Feature extraction Machine learning Mean average precision (MAP) Methods Performance enhancement Performance evaluation Point Transformer (PT) Remote sensing Retrieval Robustness Routing self-attention Shape shape classification shape retrieval Three dimensional models Three-dimensional displays Transformers
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!