Learning Indoor Layouts from Simple Point-Clouds

TL;DR

This paper introduces two deep learning methods to automatically generate indoor floor plans from smartphone-acquired point-cloud data, effectively recognizing room layouts with high accuracy.

Contribution

It presents novel neural network approaches, using Pointer Networks and Mask-RCNN, for reconstructing indoor layouts from point-clouds without manual mapping.

Findings

Achieved 0.80-0.90 IoU scores in room recognition

Demonstrated effectiveness across diverse datasets

Provided automated indoor layout generation from simple point-clouds

Abstract

Reconstructing a layout of indoor spaces has been a crucial part of growing indoor location based services. One of the key challenges in the proliferation of indoor location based services is the unavailability of indoor spatial maps due to the complex nature of capturing an indoor space model (e.g., floor plan) of an existing building. In this paper, we propose a system to automatically generate floor plans that can recognize rooms from the point-clouds obtained through smartphones like Google's Tango. In particular, we propose two approaches - a Recurrent Neural Network based approach using Pointer Network and a Convolutional Neural Network based approach using Mask-RCNN to identify rooms (and thereby floor plans) from point-clouds. Experimental results on different datasets demonstrate approximately 0.80-0.90 Intersection-over-Union scores, which show that our models can effectively identify the rooms and regenerate the shapes of the rooms in heterogeneous environment.