arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.01232cs.CV
收藏

球面对准:用于摄像机位姿估计的全局最优球面混合对准

The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation

Australian National University(澳大利亚国立大学);Data61/CSIRO(Data61/联邦科学与工业研究组织);ShanghaiTech(上海科技大学)

Dylan Campbell, Lars Petersson, Laurent Kneip, Hongdong Li, Stephen Gould

摘要:

从单个图像确定校准相机相对于3D模型的位置和方向是许多应用的基本任务。当可以可靠地获得2D-3D对应关系时,可以使用透视n点解算器来恢复相机姿态。然而,在没有姿态的情况下,找到2D图像和3D模型之间的跨模态对应关系是不平凡的,特别是当后者仅包含几何信息时。因此,问题变成联合估计姿态和对应关系的问题。由于离群值和局部最优值是如此普遍,鲁棒的目标函数和全局搜索策略是可取的。因此,我们投的问题作为一个2D-3D的混合模型对齐任务,并提出了第一个全局最优的解决方案,这个配方下的强大的$L_2$混合分布之间的距离。我们使用分支定界搜索6D相机姿态空间,这需要新的边界,以避免姿态估计的需要并保证全局最优性。为了加速收敛,我们集成了局部优化,实现了GPU边界计算,并提供了一种直观的方式来整合语义标签等辅助信息。该算法在具有挑战性的合成和真实数据集上进行评估,优于现有方法,并可靠地收敛到全局最优值。

英文摘要:

Determining the position and orientation of a calibrated camera from a single image with respect to a 3D model is an essential task for many applications. When 2D-3D correspondences can be obtained reliably, perspective-n-point solvers can be used to recover the camera pose. However, without the pose it is non-trivial to find cross-modality correspondences between 2D images and 3D models, particularly when the latter only contains geometric information. Consequently, the problem becomes one of estimating pose and correspondences jointly. Since outliers and local optima are so prevalent, robust objective functions and global search strategies are desirable. Hence, we cast the problem as a 2D-3D mixture model alignment task and propose the first globally-optimal solution to this formulation under the robust $L_2$ distance between mixture distributions. We search the 6D camera pose space using branch-and-bound, which requires novel bounds, to obviate the need for a pose estimate and guarantee global optimality. To accelerate convergence, we integrate local optimization, implement GPU bound computations, and provide an intuitive way to incorporate side information such as semantic labels. The algorithm is evaluated on challenging synthetic and real datasets, outperforming existing approaches and reliably converging to the global optimum.

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。

↑