Smart hypothesis generation for efficient and robust room layout estimation

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem Konferenzband

Abstract

We propose a novel method to efficiently estimate the spatial layout of a room from a single monocular RGB image. As existing approaches based on low-level feature extraction, followed by a vanishing point estimation are very slow and often unreliable in realistic scenarios, we build on semantic segmentation of the input image. To obtain better segmentations, we introduce a robust, accurate and very efficient hypothesize-and-test scheme. The key idea is to use three segmentation hypotheses, each based on a different number of visible walls. For each hypothesis, we predict the image locations of the room corners and select the hypothesis for which the layout estimated from the room corners is consistent with the segmentation. We demonstrate the efficiency and robustness of our method on three challenging benchmark datasets, where we significantly outperform the state-of-the-art.
Originalspracheenglisch
TitelProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
Seiten2901-2909
Seitenumfang9
ISBN (elektronisch)978-1-7281-6553-0
DOIs
PublikationsstatusVeröffentlicht - 1 Mär 2020
Veranstaltung2020 IEEE/CVF Winter Conference on Applications of Computer Vision: WACV 2020 - Snowmass Village, USA / Vereinigte Staaten
Dauer: 1 Mär 20205 Mär 2020

Publikationsreihe

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Konferenz

Konferenz2020 IEEE/CVF Winter Conference on Applications of Computer Vision
KurztitelWACV 2020
LandUSA / Vereinigte Staaten
OrtSnowmass Village
Zeitraum1/03/205/03/20

ASJC Scopus subject areas

  • !!Computer Vision and Pattern Recognition
  • !!Computer Science Applications

Dieses zitieren