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

CVPR 2019 Shang-Ta YangFu-En WangChi-Han PengPeter WonkaMin SunHung-Kuo Chu

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... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
3D Room Layouts From A Single Rgb Panorama PanoContext DuLa-Net 3DIoU 77.42% # 3
3D Room Layouts From A Single Rgb Panorama Realtor360 DuLa-Net 3DIoU 77.20% # 1
3D Room Layouts From A Single Rgb Panorama Stanford 2D-3D DuLa-Net 3DIoU 79.36% # 2