PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
复制标题
DOI：
10.1109/cvpr52688.2022.00842
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Haiyan Wang;Will Hutchcroft;Yuguang Li;Zhiqiang Wan;Ivaylo Boyadzhiev;Yingli Tian;S. B. Kang
中科院分区：
文献类型：
--
作者：
Haiyan Wang;Will Hutchcroft;Yuguang Li;Zhiqiang Wan;Ivaylo Boyadzhiev;Yingli Tian;S. B. Kang
在本文中，我们提出了一种新的基于深度学习的方法，用于在给定一对360°全景图的情况下估计房间布局。我们的系统，称为位置感知立体融合网络或PSMNet，是一个端到端的联合布局姿态估计器。PSMNet由一个立体全景姿态（SP2）Transformer和一个新的交叉透视投影（CP2）层组成。立体视图SP2 Transformer用于隐式地推断视图之间的对应关系，并且可以处理噪声姿态。姿态感知的CP2层被设计为将来自相邻视图的特征渲染到锚（参考）视图，以便执行视图融合并估计可见布局。我们的实验和分析验证了我们的方法，它显着优于最先进的布局估计，特别是对于大型和复杂的房间空间。
In this paper, we propose a new deep learning-based method for estimating room layout given a pair of 360° panoramas. Our system, called Position-aware Stereo Merging Network or PSMNet, is an end-to-end joint layout-pose estimator. PSMNet consists of a Stereo Pano Pose (SP2) transformer and a novel Cross-Perspective Projection (CP2) layer. The stereo-view SP2 transformer is used to implicitly infer correspondences between views, and can handle noisy poses. The pose-aware CP2 layer is designed to render features from the adjacent view to the anchor (reference) view, in order to perform view fusion and estimate the visible layout. Our experiments and analysis validate our method, which significantly outperforms the state-of-the-art layout estimators, especially for large and complex room spaces.