LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image

CVPR 2018  ·  Chuhang Zou, Alex Colburn, Qi Shan, Derek Hoiem ·

We propose an algorithm to predict room layout from a single image that generalizes across panoramas and perspective images, cuboid layouts and more general layouts (e.g. L-shape room). Our method operates directly on the panoramic image, rather than decomposing into perspective images as do recent works. Our network architecture is similar to that of RoomNet, but we show improvements due to aligning the image based on vanishing points, predicting multiple layout elements (corners, boundaries, size and translation), and fitting a constrained Manhattan layout to the resulting predictions. Our method compares well in speed and accuracy to other existing work on panoramas, achieves among the best accuracy for perspective images, and can handle both cuboid-shaped and more general Manhattan layouts.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Room Layouts From A Single RGB Panorama PanoContext LayoutNet 3DIoU 74.48% # 4
3D Room Layouts From A Single RGB Panorama Realtor360 LayoutNet 3DIoU 62.77% # 2
3D Room Layouts From A Single RGB Panorama Stanford 2D-3D LayoutNet 3DIoU 76.33% # 3

Methods


No methods listed for this paper. Add relevant methods here