Semantic Room Wireframe Detection from a Single View
TL
TL;DR
It is shown 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.
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.
References46 items
1
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
2
LGNN: A Context-aware Line Segment Detector
3
Holistically-Attracted Wireframe Parsing
4
3D Room Layout Estimation From a Single RGB Image
5