arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.14166cs.CV
收藏

基于分治法的室内全景平面三维重建

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

National Tsing Hua University(国立清华大学);ASUS AICS(华硕AI研发中心);Joint Research Center for AI Technology and All Vista Healthcare(AI技术与All Vista Healthcare联合研究中心);Aeolus Robotics

Cheng Sun, Chi-Wei Hsiao, Ning-Hsu Wang, Min Sun, Hwann-Tzong Chen

摘要:

室内全景通常由平行或垂直于重力的人造结构组成。我们利用这种现象来近似场景中的360度图像与(H)orizontal-planes和(V)ertical-planes。为此,我们提出了一种有效的分治策略,划分像素的基础上,他们的平面方向估计,然后,后续的实例分割模块征服的任务,更容易在每个平面方向组的平面聚类。此外,V平面的参数取决于摄像机的偏航旋转,但平移不变的CNN不太了解偏航变化。因此,我们提出了一个偏航不变的V平面重新参数化CNN学习。我们通过扩展现有的360深度数据集与地面真实H\& V平面(称为PanoH&V数据集),并采用最先进的平面重建方法来预测H\& V平面作为我们的基线,创建了一个室内全景平面重建的基准。我们的方法在所提出的数据集上的性能大大优于基线。

英文摘要:

Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity. We leverage this phenomenon to approximate the scene in a 360-degree image with (H)orizontal-planes and (V)ertical-planes. To this end, we propose an effective divide-and-conquer strategy that divides pixels based on their plane orientation estimation; then, the succeeding instance segmentation module conquers the task of planes clustering more easily in each plane orientation group. Besides, parameters of V-planes depend on camera yaw rotation, but translation-invariant CNNs are less aware of the yaw change. We thus propose a yaw-invariant V-planar reparameterization for CNNs to learn. We create a benchmark for indoor panorama planar reconstruction by extending existing 360 depth datasets with ground truth H\&V-planes (referred to as PanoH&V dataset) and adopt state-of-the-art planar reconstruction methods to predict H\&V-planes as our baselines. Our method outperforms the baselines by a large margin on the proposed dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑