CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis

TL;DR

This paper introduces CubiCasa5K, a large-scale annotated floorplan dataset, and an improved multi-task neural network model to advance automatic floorplan image analysis for AR/VR applications.

Contribution

The paper provides a new comprehensive dataset and an improved neural network model, enabling more effective and detailed analysis of floorplan images.

Findings

CubiCasa5K contains 5000 annotated floorplan images with over 80 object categories.

The proposed multi-task model outperforms previous approaches in floorplan object segmentation.

The dataset and model facilitate more accurate and versatile floorplan image understanding.

Abstract

Better understanding and modelling of building interiors and the emergence of more impressive AR/VR technology has brought up the need for automatic parsing of floorplan images. However, there is a clear lack of representative datasets to investigate the problem further. To address this shortcoming, this paper presents a novel image dataset called CubiCasa5K, a large-scale floorplan image dataset containing 5000 samples annotated into over 80 floorplan object categories. The dataset annotations are performed in a dense and versatile manner by using polygons for separating the different objects. Diverging from the classical approaches based on strong heuristics and low-level pixel operations, we present a method relying on an improved multi-task convolutional neural network. By releasing the novel dataset and our implementations, this study significantly boosts the research on automatic floorplan image analysis as it provides a richer set of tools for investigating the problem in a more comprehensive manner.