Semantic Room Wireframe Detection from a Single View
Gillsjö, David; Flood, Gabrielle; Åström, Kalle (2022-08-25). Semantic Room Wireframe Detection from a Single View 26th International Conference on Pattern Recognition, 2022, 1886 - 1893. 26TH International Conference on Pattern Recognition, 2022. Montreal, Canada: IEEE - Institute of Electrical and Electronics Engineers Inc.
Conference Proceeding/Paper
|
Published
|
English
Authors:
Gillsjö, David
;
Flood, Gabrielle
;
Åström, Kalle
Department:
Mathematics (Faculty of Engineering)
eSSENCE: The e-Science Collaboration
ELLIIT: the Linköping-Lund initiative on IT and mobile communication
LTH Profile Area: AI and Digitalization
Stroke Imaging Research group
Mathematical Imaging Group
LTH Profile Area: Engineering Health
Project:
Semantic Structure from Motion
Research Group:
Stroke Imaging Research group
Mathematical Imaging Group
Abstract:
Reconstruction of indoor surfaces with limited texture information or with repeated textures, a situation common in walls and ceilings, may be difficult with a monocular Structure from Motion system. We propose a Semantic Room Wireframe Detection task to predict a Semantic Wireframe from a single perspective image. Such predictions may be used with shape priors to estimate the Room Layout and aid reconstruction. To train and test the proposed algorithm we create a new set of annotations from the simulated Structured3D dataset. We show qualitatively that the SRW-Net handles complex room geometries better than previous Room Layout Estimation algorithms while quantitatively out-performing the baseline in non-semantic Wireframe Detection.
Cite this