Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation

TL;DR

This paper introduces a fast and reliable method for estimating room layouts from a single RGB image by leveraging semantic segmentation and a hypothesis testing scheme based on different visible wall configurations.

Contribution

The authors present a novel hypothesis-based approach that improves efficiency and robustness over existing low-level feature methods for room layout estimation.

Findings

Outperforms state-of-the-art on three benchmark datasets.

Achieves higher accuracy in room corner prediction.

Demonstrates significant speed improvements.

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.