We propose an approach for estimating the relative pose between calibrated
image pairs by jointly exploiting points, lines, and their coincidences in a
hybrid manner. We investigate all possible configurations where these data
modalities can be used together and review the minimal solvers available in the
literature. Our hybrid framework combines the advantages of all configurations,
enabling robust and accurate estimation in challenging environments. In
addition, we design a method for jointly estimating multiple vanishing point
correspondences in two images, and a bundle adjustment that considers all
relevant data modalities. Experiments on various indoor and outdoor datasets
show that our approach outperforms point-based methods, improving
AUC@10$^\circ$ by 1-7 points while running at comparable speeds. The source
code of the solvers and hybrid framework will be made public.

我们提出了一种估计已标定图像对之间相对位姿的方法，通过综合利用点、线及它们在混合方式下的重合情况。我们研究了这些数据模态可以共同使用的所有可能配置，并回顾了文献中可用的最小求解器。我们的混合框架结合了所有配置的优点，在具有挑战性的环境中实现了稳健准确的估计。此外，我们设计了一种方法，可以联合估计两幅图像中的多个消失点对应，并进行了包括所有相关数据模态的束调整。各种室内外数据集上的实验证明我们的方法优于基于点的方法，在可比速度下将 AUC@10° 提升了 1-7 个点。解算器和混合框架的源代码将公开发布。