HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation

CVPR 2019 Cheng SunChi-Wei HsiaoMin SunHwann-Tzong Chen

We present a new approach to the problem of estimating the 3D room layout from a single panoramic image. We represent room layout as three 1D vectors that encode, at each image column, the boundary positions of floor-wall and ceiling-wall, and the existence of wall-wall boundary... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
3D Room Layouts From A Single Rgb Panorama PanoContext HorizonNet 3DIoU 82.17% # 1
3D Room Layouts From A Single Rgb Panorama Stanford 2D-3D HorizonNet 3DIoU 79.79% # 1