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

We present a new approach to the problem of estimating the 3D room layoutfrom a single panoramic image. We represent room layoutas 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. The proposed network, HorizonNet, trained for predicting 1D layout, outperforms previous state-of-the-art approaches. The designed post-processing procedure for recovering 3D room layoutsfrom 1D predictions can automatically infer the room shape with low computation cost - it takes less than 20ms for a panorama image while prior works might need dozens of seconds. We also propose Pano Stretch Data Augmentation, which can diversify panorama data and be applied to other panorama-related learning tasks. Due to the limited data available for non- cuboid layout, we relabel 65 general layoutfrom the current dataset for finetuning. Our approach shows good performance on general layoutsby qualitative results and cross-validation.