Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

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
FachzeitschriftarXiv.org e-Print archive
PublikationsstatusVeröffentlicht - 2019

Fingerprint

Feature extraction
Semantics

Dies zitieren

Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation. / Hirzer, Martin; Roth, Peter M.; Lepetit, Vincent.

in: arXiv.org e-Print archive, 2019.

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

@article{55a9b5771073431d960515d1d6b718d8,
title = "Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation",
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.",
author = "Martin Hirzer and Roth, {Peter M.} and Vincent Lepetit",
year = "2019",
language = "English",
journal = "arXiv.org e-Print archive",
publisher = "Cornell University Library",

}

TY - JOUR

T1 - Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation

AU - Hirzer, Martin

AU - Roth, Peter M.

AU - Lepetit, Vincent

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

M3 - Article

JO - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

ER -