DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama

Shang-Ta Yang, Fu-En Wang, Chi-Han Peng, Peter Wonka, Min Sun, Hung-Kuo Chu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Scopus citations

Abstract

We present a deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama. To achieve better prediction accuracy, our method leverages two projections of the panorama at once, namely the equirectangular panorama-view and the perspective ceiling-view, that each contains different clues about the room layouts. Our network architecture consists of two encoder-decoder branches for analyzing each of the two views. In addition, a novel feature fusion structure is proposed to connect the two branches, which are then jointly trained to predict the 2D floor plans and layout heights. To learn more complex room layouts, we introduce the Realtor360 dataset that contains panoramas of Manhattan-world room layouts with different numbers of corners. Experimental results show that our work outperforms recent state-of-the-art in prediction accuracy and performance, especially in the rooms with non-cuboid layouts.
Original languageEnglish (US)
Title of host publication2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages3358-3367
Number of pages10
ISBN (Print)9781728132938
DOIs
StatePublished - 2019

Fingerprint

Dive into the research topics of 'DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama'. Together they form a unique fingerprint.

Cite this