论文标题
Geolayout：基于平面深度图的几何驱动房间布局估算
GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes
论文作者
论文摘要
房间布局估计的任务是定位墙壁地板，墙壁天花板和墙壁边界。最新方法基于边缘/关键点检测或语义分割解决了此问题。但是，这些方法表明，人们对主要平面的几何形状及其之间的交集有限，这对房间的布局产生了重大影响。在这项工作中，我们建议将几何推理纳入深入学习，以进行布局估计。我们的方法学会通过预测像素级表面参数来推断场景中主要平面的深度图，并且可以通过深度图的交点来生成布局。此外，我们提出了一个新的数据集，其中具有像素级的深度注释。它大于现有数据集，并且包含立方体和非生物房间。实验结果表明，我们的方法在2D和3D数据集上都会产生可观的性能增长。
The task of room layout estimation is to locate the wall-floor, wall-ceiling, and wall-wall boundaries. Most recent methods solve this problem based on edge/keypoint detection or semantic segmentation. However, these approaches have shown limited attention on the geometry of the dominant planes and the intersection between them, which has significant impact on room layout. In this work, we propose to incorporate geometric reasoning to deep learning for layout estimation. Our approach learns to infer the depth maps of the dominant planes in the scene by predicting the pixel-level surface parameters, and the layout can be generated by the intersection of the depth maps. Moreover, we present a new dataset with pixel-level depth annotation of dominant planes. It is larger than the existing datasets and contains both cuboid and non-cuboid rooms. Experimental results show that our approach produces considerable performance gains on both 2D and 3D datasets.
