TartanVO: A Generalizable Learning-based VO

Contributions：

First, we demonstrate the crucial effects of data diversity on the generalization ability of a VO model by comparing performance on different quantities of training data. （deeplearning 的痛点 误差找到姿态变化丰富的数据集，作者采用合成的办法，可以提供各种各样的变换姿态的GT）

 Second, we design an up-to-scale loss function to deal with the scale ambiguity of monocular VO. （通过归一化的方式，解决尺度歧义的问题）Third, we create an intrinsics layer (IL) in our VO model enabling generalization across different cameras. （提出了一个内参层，解决训练集合测试集内参不一样造成的问题）