Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

TL;DR

This paper introduces a neural network-based method for reconstructing 3D room layouts from a single RGB image, moving beyond cuboid assumptions to more general room shapes with effective geometric reasoning.

Contribution

It proposes a novel approach combining CNN-based plane detection and geometric optimization for non-cuboid room layout reconstruction from a single image.

Findings

Effective reconstruction of non-cuboid room layouts.

Outperforms previous methods on public datasets.

Efficient geometric reasoning improves accuracy.

Abstract

Single-image room layout reconstruction aims to reconstruct the enclosed 3D structure of a room from a single image. Most previous work relies on the cuboid-shape prior. This paper considers a more general indoor assumption, i.e., the room layout consists of a single ceiling, a single floor, and several vertical walls. To this end, we first employ Convolutional Neural Networks to detect planes and vertical lines between adjacent walls. Meanwhile, estimating the 3D parameters for each plane. Then, a simple yet effective geometric reasoning method is adopted to achieve room layout reconstruction. Furthermore, we optimize the 3D plane parameters to reconstruct a geometrically consistent room layout between planes and lines. The experimental results on public datasets validate the effectiveness and efficiency of our method.