GeoSynth: A Photorealistic Synthetic Indoor Dataset for Scene Understanding

Deep learning has revolutionized many scene perception tasks over the past decade. Some of these improvements can be attributed to the development of large labeled datasets. The creation of such datasets can be an expensive, time-consuming, and imperfect process. To address these issues, we introduc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on visualization and computer graphics 2023-05, Vol.29 (5), p.2586-2595
Hauptverfasser:	Pugh, Brian, Chernak, Davin, Jiddi, Salma
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations artificial intelligence Datasets mesh modeling Perception ray tracing Rendering Rendering (computer graphics) Scene analysis Semantic segmentation Synthetic data synthetic dataset Task analysis Three-dimensional displays Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!