We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.

翻译：我们提出学习一种深度协方差函数，并将其应用于几何视觉任务。以RGB图像为输入，该协方差函数可灵活用于定义深度函数的先验、给定观测条件下的预测分布以及主动点选择方法。我们利用这些技术完成一系列下游任务：深度补全、光束法平差和单目稠密视觉里程计。