Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs

Estimating the layout of a room from a single-shot panoramic image is important in virtual/augmented reality and furniture layout simulation. This involves identifying three-dimensional (3D) geometry, such as the location of corners and boundaries, and performing 3D reconstruction. However, occlusio...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-04
Hauptverfasser:	Tabata, Mizuki, Kurata, Kana, Tamamatsu, Junichiro
Format:	Artikel
Sprache:	eng
Schlagworte:	Augmented reality Corners Datasets Distillation Estimation Image reconstruction Layouts Occlusion Three dimensional models Virtual reality
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!